https://cybertoolchain.io/tools/ai-infra-guard New releases and features in AI-Infra-Guard, tracked by The Cyber Toolchain. en Thu, 29 Oct 2026 04:02:30 GMT https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.8 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.8 Thu, 29 Oct 2026 04:02:30 GMT AI-Infra-Guard adds a Runcrate provider preset to Agent-Scan and packages each scanner for independent pip install⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Install any scanner on its own without pulling the full tool by packaging each scanner for an independent `pip install`.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Agent-Scan now supports Runcrate as a provider preset, expanding the range of agent runtimes it can target. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.7 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.7 Thu, 22 Oct 2026 04:03:24 GMT Agent-Scan gains AG-UI (CopilotKit) protocol stream support, a cheaper inference provider preset, and daily AI CVE advisories plus astron-agent fingerprinting.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds `astron-agent` fingerprint to the data layer for AI infrastructure detection.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds a Cheaper Inference provider preset to Agent-Scan for cost-sensitive scan configurations. • Agent-Scan now forwards the prompt and selected skills to the scanner, giving operators direct control over scan inputs. • Supports AG-UI (CopilotKit) protocol streams in Agent-Scan, enabling scanning of CopilotKit-backed agents. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.6 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.6 Thu, 15 Oct 2026 04:03:13 GMT AI-Infra-Guard v4.6.6 adds Atlas Cloud and API Route agent presets, memory/RAG poisoning detection, JSON scan output, and a bilingual BadPhoneAgent benchmark.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds Atlas Cloud provider preset to Agent-Scan, enabling out-of-the-box scanning of Atlas Cloud-hosted AI agents.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds API Route provider preset to Agent-Scan, covering API-routed agent surfaces without manual configuration. • Adds a memory/RAG poisoning detection skill to Agent-Scan, surfacing data-poisoning attacks against retrieval-augmented generation pipelines. • Adds `extra_headers` / `extra_body` editing to the Dashboard model dialog, letting operators inject custom HTTP headers and body fields per model provider. • Adds BadPhoneAgent bilingual benchmark to Eval, extending jailbreak evaluation coverage with a new dual-language phone-agent attack scenario. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.4 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.4 Thu, 01 Oct 2026 04:09:31 GMT Adds pikit, a composable prompt-injection research toolkit, under Research/pikit⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Vendors `pikit` (NY1024/pikit), a composable prompt-injection research toolkit, under `Research/pikit`⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.3 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.3 Thu, 24 Sep 2026 04:01:35 GMT DeepTeam now flushes finished test cases to disk mid-run; API Checker gets more reliable model fingerprinting via sample refilling.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds mid-run disk persistence for DeepTeam: finished test cases are written to disk during a run rather than held only in memory.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Improves API Checker model identification by refilling failed fingerprint samples for more reliable detection. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.2 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.2 Thu, 17 Sep 2026 04:02:04 GMT AI-Infra-Guard v4.6.2 adds FORGE-Bench loss-of-control benchmark and RogueHandoff-20 benchmark for autonomous agent red teaming.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds `forge_bench` (FORGE-Bench) — a deterministic Loss-of-Control benchmark for evaluating autonomous agents, with a built-in OpenAI-compatible client and bilingual quickstart.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds RogueHandoff-20 benchmark under the Research module for autonomous agent handoff security evaluation. • Updates AIG rules dataset (2026-09-11 ruleset). Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.1 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.1 Thu, 10 Sep 2026 09:18:51 GMT AI-Infra-Guard v4.6.1 adds Gemini, Gemma, and GLM fingerprints to the API Checker.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds Gemini, Gemma, and GLM fingerprints to the API Checker for model identification.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Updates the GLM-5.3-Flash fingerprint baseline in the API Checker. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.0 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.0 Wed, 26 Aug 2026 11:15:00 GMT AI-Infra-Guard v4.6.0 adds an API security audit module, LLM API poisoning detection, and a v5.0.0 mutation engine for agent red-teaming. • Adds detection for LLM API poisoning attacks. • Merges `workflow-attack` into `mutation-attack` in the `aig-agent-redteam` v5.0.0 mutation engine refactor. • Adds strict YAML validation enforcing required `id` and `severity` fields in vulnerability rules. • Includes DeepSeek Harness prompt injection assessment research. • Updates AIG vulnerability rules with two new rule-set snapshots dated 2026-08-07 and 2026-08-14. Breaking changes: • The `workflow-attack` subcommand/mode in `aig-agent-redteam` is merged into `mutation-attack`; any automation invoking `workflow-attack` will need to be updated. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.5.2 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.5.2 Mon, 17 Aug 2026 02:30:47 GMT AI-Infra-Guard v4.5.2 adds SkillJack research, GET-only fingerprints for Qdrant/Chroma/Weaviate, and a v5.0.0 mutation engine refactor merging workflow-attack into mutation-attack. • Adds GET-only fingerprints for Qdrant, Chroma, and Weaviate to the fingerprint library, enabling passive identification of these vector databases. • Introduces the SkillJack research project, expanding the platform's AI security research surface. • Upgrades the `aig-agent-redteam` skill to v5.0.0 with a refactored mutation engine that merges `workflow-attack` into `mutation-attack` for consolidated adversarial testing. • Adds new AIG detection rules dated 2026-07-31. Breaking changes: • The `aig-agent-redteam` skill's `workflow-attack` has been merged into `mutation-attack`; any automation or config referencing `workflow-attack` as a separate attack mode will need to be updated. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.5.1 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.5.1 Thu, 30 Jul 2026 07:48:52 GMT AI-Infra-Guard v4.5.1 adds multi-turn jailbreak attacks, 6 new OWASP agent-scan skills, and 4 new MCP security detection rules. • Adds Many-Shot, PAIR, GOAT, and ActorAttack multi-turn jailbreak attack methods to PromptSecurity. • Adds 5 new OWASP-aligned Agent-Scan detection skills: agentic-supply-chain, cascading-failure, human-agent-trust, inter-agent-comm, and unexpected-code-execution. • Adds web-exfiltration-detection skill to Agent-Scan. • Adds 4 new MCP-Scan security detection rules covering hardcoded secrets and insecure deserialization. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.5.0 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.5.0 Mon, 27 Jul 2026 07:21:58 GMT AI-Infra-Guard v4.5.0 adds standalone CLI modules for Agent/MCP/Skill scanning, new AI agent detection skills, SARIF output, and open-source frontend. • Modularizes Agent-Scan as a standalone CLI with AIG integration support, adding 4 new AI agent security detection skills. • Modularizes MCP-Scan with dual-mode support (CLI + AIG Web) and adds a standalone mcp-scan-lite module. • Adds 2 new MCP security detection rules plus ATR-derived MCP detection rules covering additional attack surfaces. • Adds Agent Skill security auditing (Skill-Scan) repackaged as the standalone PyPI package `aig-skill-scan`. • Adds SARIF 2.1.0 output format for Skill-Scan results alongside single-stage optimization. • Adds Stage 2 Code Audit Markdown report output for Skill-Scan (replacing XML). • Adds `agentic-tool-misuse` evaluation dataset for assessing agentic tool misuse scenarios. • Open-sources the frontend code with open-source environment configuration. • Adds new AI component fingerprints and AIG vulnerability rules from June–July 2026 rule updates. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.15 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.15 Thu, 25 Jun 2026 04:02:51 GMT Adds `mcp_scan` and `ai_infra_scan` model token flexibility; new MCP threat detections • `mcp_scan` and `ai_infra_scan` commands now allow omitting the model token argument to fall back to the system default model instead of failing. • New MCP threat detection rules added for tool poisoning, credential exfiltration, and command injection. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.15 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.15 Thu, 25 Jun 2026 04:02:51 GMT AI-Infra-Guard v4.1.15 adds optional model token in scan APIs, 6 new llama.cpp CVE rules, and 3 new MCP threat detection rules. • Supports omitting the model token in `mcp_scan` and `ai_infra_scan` API calls, falling back to the system default model. • Adds 6 new llama.cpp CVE detection rules to the llama-cpp vulnerability pack. • Adds 3 new MCP threat detection rules covering tool poisoning, credential exfiltration, and command injection. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.14 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.14 Thu, 18 Jun 2026 04:02:16 GMT AI-Infra-Guard v4.1.14 adds aig-agent-redteam skill, 9 new jailbreak methods, and eval datasets • Adds `aig-agent-redteam` skill for Agent security assessment • Adds 9 single-turn jailbreak attack methods: PrefillAttack, ICA, PastTense, Overload, Jailbroken, FlipAttack, DeepInception, CodeChameleon, JAM • Adds jailbreak evaluation datasets AdvBench, CNSafe, SafeBench Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.13 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.13 Thu, 11 Jun 2026 04:02:54 GMT AI-Infra-Guard v4.1.13 adds a version check API endpoint • Adds the `/version` (or equivalent) endpoint for programmatic version checking Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.12 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.12 Mon, 08 Jun 2026 02:42:24 GMT v4.1.12 adds 39 new AI web fingerprints and enhances 18 existing ones for AI infrastructure detection • Adds support for 39 new AI web fingerprints to detect additional AI services and frameworks Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.10 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.10 Thu, 28 May 2026 04:04:18 GMT Adds `--websocket` support for agent providers in AI-Infra-Guard v4.1.10 • Supports WebSocket agent providers, enabling connections to inference endpoints that communicate over the WebSocket protocol. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.9 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.9 Thu, 21 May 2026 04:04:38 GMT AI-Infra-Guard v4.1.9 adds 20+ single-turn and 6 multi-turn prompt attack operators for red-teaming. • Adds `invisible-text`, `case-formatting`, `script-system`, `unicode-style`, `classical-cipher`, `classic-encoding`, `SystemOverride`, `SuperUser`, `LinguisticConfusion`, `Roleplay`, `PromptProbing`, `PromptInjection`, `PROMISQROUTE`, `PermissionEscalation`, `Multilingual`, `MathProblem`, `InputBypass`, `ICRTJailbreak`, `GrayBox`, `GoalRedirection`, `EquaCode`, and `ContextPoisoning` as single-turn prompt attack operators. • Adds `TreeJailbreaking`, `SequentialJailbreaking`, `LinearJailbreaking`, `CrescendoJailbreaking`, `BestofN`, and `BadLikertJudge` as multi-turn prompt attack operators. • Registers newly added attack operators in the documentation. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.6 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.6 Thu, 23 Apr 2026 08:45:20 GMT v4.1.6 adds detection for exposed AI agent configs (claude_desktop_config.json, mcp.json), manual dataset updates, and merges the update-status API into update-data. • Adds `update-data` endpoint merging previous update-status functionality • Supports manual updates to latest jailbreak datasets, fingerprints, and vulnerability databases • Detects exposed AI agent config files like `claude_desktop_config.json` and `mcp.json` • Extends `.env` key patterns for broader secret coverage Breaking changes: • The `/update-status` endpoint is removed; use `update-data` instead. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.4 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.4 Fri, 17 Apr 2026 10:44:58 GMT v4.1.4 adds MCP red team scan, data sync APIs, and self-signed TLS support for model endpoints • Add `--agent-config-file` CLI flag to pass inline YAML agent scan config (requires aig-scanner v1.0.3) • Add `InsecureSkipVerify` option to bypass TLS verification for HTTPS connections with self-signed/private CA certificates • Add multi-turn red team attack module supporting TAP and Crescendo strategies in MCP Scan • Add `POST /api/v1/system/update-data` and `GET /api/v1/system/update-status` endpoints for auto-syncing the `data/` directory • Support inline `agent_config` in Agent Scan API with optional verify flag on save Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.2 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.2 Fri, 03 Apr 2026 08:46:24 GMT AI-Infra-Guard v4.1.2 adds support for stopping running tasks via task control • Added support for stopping running tasks, allowing users to actively terminate scans in progress Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.1 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1.1 Wed, 25 Mar 2026 08:29:13 GMT AI-Infra-Guard v4.1.1 adds FOFA API fingerprint matching syntax and new AIG vulnerability rules. • Adds correct new-api fingerprint matcher syntax (FOFA 100%) to enable precise fingerprinting via FOFA • Integrates AIG rules batch from 2026-03-25 to expand AI component vulnerability detection Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.1 Mon, 23 Mar 2026 03:51:54 GMT AI-Infra-Guard v4.1 adds OpenClaw coverage, EdgeOne ClawScan skill, and task API enhancements • Adds port 18789 to the default AI infrastructure scan port list • AIG Rules (2026-03-20 batch) for AI component vulnerability detection • New OpenClaw vulnerability database with 281 CVE/GHSA entries • Adds EdgeOne-based ClawScan security scanning Skill to agent capabilities • Task API now supports enhanced Agent Scan and lifecycle management Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.0 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.0 Tue, 10 Mar 2026 12:30:21 GMT AI-Infra-Guard v4.0 introduces the Agent-Scan framework, ClawScan integration, and new AI component fingerprints. • `EdgeOne ClawScan` provides a dedicated security portal for OpenClaw via [https://matrix.tencent.com/clawscan/](https://matrix.tencent.com/clawscan/openclaw). • New `Agent-Scan` framework introduces a multi-agent architecture with specialized agents (SSRF, config-scanner, vulnerability detector, etc.) for autonomous agent security scanning. • Added fingerprints for `llama.cpp`, `HuggingFace TGI`, `NVIDIA NIM`, and `LocalAI` in component detection. • `Agent-Scan` simulates interactions using actions: `bash`, `file read/write`, `edit`, `grep`, `glob`, `ls`, `batch`, `thinking`, `todo`, `task`, `skill`, `MCP tool`, `dialogue`, and `finish`. Breaking changes: • Removed the `idSuffix` field from configuration. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.6.2 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.6.2 Mon, 09 Feb 2026 03:17:37 GMT Adds `n8n` fingerprint for AI infrastructure scanning • Added `n8n` fingerprint to detect n8n-based automation workflows in scanned environments Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.6.0 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.6.0 Sat, 17 Jan 2026 15:02:44 GMT AI-Infra-Guard v3.6.0 adds inner API auth controller and SYS_ADMIN capability for Chrome sandbox. • Adds inner API auth controller to handle authentication for internal API endpoints • Adds SYS_ADMIN capability for Chrome sandbox and database indexes for performance enhancement Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.5.0 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.5.0 Fri, 26 Dec 2025 08:53:57 GMT AI-Infra-Guard v3.5.0 adds dynamic analysis framework, MCP remote tool invocation, and new detection types • Adds `Dynamic Analysis Framework` with specialized agents for malicious behavior and vulnerability testing • Adds `tool poisoning detection` and `rug pull detection` capabilities • Adds support for new evaluation datasets including copyright-violation, misinformation, privacy-leakage, unethical-behavior, violent, and non-violent-illegal-activity • Adds `mcp_tool` for remote MCP server tool invocation • Adds `write_file` tool for file writing operations • Adds version router endpoint `/version` via the Version API • Adds `prompt_manager` utility for prompt template management • Adds custom `MCP Header Support` for authentication and protocol configuration • Adds frontend integration for MCP scan header configuration in the settings panel Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.5-preview https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.5-preview Thu, 04 Dec 2025 11:02:11 GMT New MCP-Scan framework, headless screenshot capabilities, and advanced encoding/obfuscation attack methods in AI-Infra-Guard v3.5-preview • Adds `MCP-Scan` framework for Model Context Protocol security scanning with autonomous agent-based code audit and vulnerability review • Adds support for 12+ new encoding/obfuscation attack methods including A1Z26, AffineCipher, AsciiSmuggling, Aurebesh, Caesar, Leetspeak, MirrorText, Ogham, Vaporwave, Zalgo, Stego, and StrataSword suite • Adds Chromium-based headless screenshot functionality for web scanning Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.4.3 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.4.3 Mon, 27 Oct 2025 06:21:50 GMT AI-Infra-Guard v3.4.3 adds Model Invocation Base Class, expanded API docs, and new evaluation datasets. • Adds `ModelInvocationBaseClass` base class methods for model invocation to improve code reusability • Updates API documentation with enhanced Swagger specifications • Expands evaluation datasets with Cyberattack and CBRN weapons test data Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.4 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.4 Thu, 18 Sep 2025 06:54:49 GMT AI-Infra-Guard v3.4 adds Docker ARM support, task concurrency limits, and i18n to the CLI. • Adds Apple ARM architecture deployment support via the updated one-click Docker script • Adds frontend internationalization (i18n) support for multi-language text display Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.2 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v3.2 Tue, 26 Aug 2025 11:10:02 GMT AI-Infra-Guard v3.2 adds model concurrency limit to MCP scans and improves report display • Optimizes MCP Scan Report data dimensions and narrow-screen layout Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v2.5 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v2.5 Thu, 12 Jun 2025 09:42:25 GMT AI-Infra-Guard v2.5 adds file size to list_dir, multi-param agent support, and MCP prompt improvements • `list_dir` now displays file sizes in its output • Agent framework refactored to support multiple parameters • MCP plugin prompts optimized for better interaction Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v2.4.1 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v2.4.1 Fri, 06 Jun 2025 02:50:16 GMT AI-Infra-Guard v2.4.1 adds parallel processing for MCP scanning to reduce latency. • Enables parallel execution for MCP (Model Context Protocol) scans to significantly improve scan throughput. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v2.1 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v2.1 Tue, 29 Apr 2025 11:54:51 GMT AI-Infra-Guard v2.1 adds MCP history saving and WebSocket stop support • `mcp` plugins now save conversation history via a dedicated parameter Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.1 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.1 Fri, 07 Mar 2025 03:33:59 GMT AI-Infra-Guard v0.1 initial release adds Xinference fingerprint support and updated vulnerability detection • Adds `xinference` fingerprint support for component detection. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.7 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.7 Wed, 26 Feb 2025 10:27:56 GMT AI-Infra-Guard v0.0.7 adds DeepSeek support and rewrites -list-vul output style • Adds `deepseek` model support for vulnerability fingerprinting queries. • Rewrites the output format of the `-list-vul` argument to display updated fingerprint information. Breaking changes: • The `--list-fps` flag has been removed; use `-list-vul` instead. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.6 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.6 Fri, 21 Feb 2025 11:16:56 GMT AI-Infra-Guard v0.0.6 adds POST fingerprint probing, websocket server, and `/show` route. • Adds `POST` request support for sending fingerprints (指纹发包) • Adds a WebSocket server to the tool's webserver • Adds `/show` route to the webserver Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.4 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.4 Thu, 13 Feb 2025 09:14:09 GMT AI-Infra-Guard v0.0.4 adds `-localscan` flag for one-click local app scanning and table output format • Adds `--localscan` (aliased as `-localscan`) to perform a one-click scan of local applications • Introduces a new table output format option for scan results Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.3 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.3 Fri, 07 Feb 2025 08:55:59 GMT v0.0.3 adds 'security advice' to output and ClickHouse fingerprint matching. • Output now includes security suggestions (`输出加入安全建议`) to guide remediation • Adds `clickhouse` fingerprint support with case-insensitive fuzzy matching (`添加clickhouse指纹`, `fuzzy匹配忽略大小写`) • Updated vulnerability fingerprints for broader detection coverage Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.2 https://github.com/Tencent/AI-Infra-Guard/releases/tag/v0.0.2 Wed, 22 Jan 2025 07:36:17 GMT AI-Infra-Guard v0.0.2 adds `-check-vul` flag for vulnerability checking and expands fingerprint support • New fingerprint added for openwebui version identification Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ai-infra-guard