https://cybertoolchain.io/tools/mend-ai New releases and features in Mend AI, tracked by The Cyber Toolchain. en Mon, 12 Oct 2026 08:08:14 GMT https://docs.mend.io/platform/latest/mend-ai-release-notes https://docs.mend.io/platform/latest/mend-ai-release-notes Mon, 12 Oct 2026 08:08:14 GMT Mend AI Runtime Protection expands Guardrails language coverage for multi-language runtime threat detection.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Expands runtime threat detection coverage in Mend AI Runtime Protection | Guardrails to additional languages.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2805-October-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2805-October-2026%29 Mon, 05 Oct 2026 00:00:00 GMT Mend AI Runtime Protection expands multi-language support for Guardrails runtime threat detection.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Expands runtime threat detection in Mend AI Runtime Protection | Guardrails to additional languages.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2827-September-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2827-September-2026%29 Sun, 27 Sep 2026 00:00:00 GMT Mend AI extends Suppress and Review triage actions to the individual finding level for more precise control.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Extends Suppress and Review triage actions to the individual finding level, enabling security teams to triage specific findings within an entity independently rather than only at the entity level.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2816-September-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2816-September-2026%29 Wed, 16 Sep 2026 00:00:00 GMT Mend AI Guardrails SDK download now requires a Mend Activation Key at install time.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds a Mend Activation Key authentication step to the Guardrails SDK installation procedure, requiring credentials at download time in addition to the existing runtime authentication.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Breaking changes: • Existing Guardrails SDK installations with unpinned versions that attempt to re-install dependencies will now require a Mend Activation Key during the install step. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2824-August-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2824-August-2026%29 Mon, 24 Aug 2026 00:00:00 GMT Mend AI adds an AI Bill of Materials (AI-BOM) report in CycloneDX 1.7 and SPDX 3.0.1 formats via UI and API. • New AI Bill of Materials (AI-BOM) report available through the Mend Platform reporting interface and API, generating a metadata-only inventory of detected AI entities — models, system prompts, agent configurations, tools, and agents — at organization, application, and project scopes. • AI-BOM exports support industry-standard CycloneDX 1.7 and SPDX 3.0.1 formats, enabling downstream tooling and compliance workflows that consume either standard. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2818-May-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2818-May-2026%29 Mon, 18 May 2026 00:00:00 GMT Mend AI 18-May-2026 adds Guardrails Docker deployment, Langflow integration, and implicit prompt detection. • `Guardrails` can now be deployed as a standalone API server with `Docker`, extending protection beyond in-app SDK integrations to any environment or language. • The `Guardrails` SDK adds `Langflow` integration for agentic workflow security. • Enhanced `Harmful Content` detection for `implicit prompts` is now available in the `Guardrails` SDK. • Mend AI’s `AI Agents Configuration Risk` feature leaves open beta and becomes generally available. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2811-May-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2811-May-2026%29 Mon, 11 May 2026 00:00:00 GMT Mend AI adds red-teaming probes, compliance mapping, and a standalone `mend ai scan` CLI command • Adds new adversarial testing capabilities including age-restricted goods, dangerous content, cross-session leaks, unverifiable claims tests, hexadecimal/Morse/emoji encoding strategies, and multi-turn escalation. • Introduces automatic mapping of red-team results to OWASP, NIST, MITRE, EU AI Act, ISO/IEC, GDPR, and DoD AI Ethics frameworks with configurable compliance thresholds. • Adds the `mend ai scan` command to enable AI scanning separately from SCA via the Mend CLI. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2804-May-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2804-May-2026%29 Mon, 04 May 2026 00:00:00 GMT Mend AI (04-May-2026): Runtime Protection open beta, streaming red teaming, custom parsers, and multi-language support • `Mend AI Runtime Protection` enters Open Beta as an in-app guardrails solution for real-time protection against prompt injection, jailbreak attempts, sensitive data exposure, and harmful content. • `Red Teaming` gains `AI model/application streaming support` and `predefined templates` tailored for specific hosting vendors. • Users can now add `custom parsers` to support proprietary applications in Red Teaming. • `Red Teaming` adds `multi-language support` enabling application simulations in different languages. • `Application status code filtering` is now available in the `HTTP connector`, allowing definition of valid versus error responses. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2808-March-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2808-March-2026%29 Sun, 08 Mar 2026 00:00:00 GMT Mend AI adds filtering by AI scan engine for scans and reports • Adds detection for all SKILL.md files regardless of their location. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2809-February-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2809-February-2026%29 Mon, 09 Feb 2026 00:00:00 GMT Mend AI adds model metadata workflows, AI findings violations management with SLAs, and System Prompt violation tracking. • Enables sophisticated workflow automation based on AI model metadata (risk factors, licensing, inference providers, authorship) for granular governance rules • Provides comprehensive violations management for AI security findings with governance workflows, SLAs, and status tracking • Adds support for violations in System Prompts including a dedicated column in the risk table, side panel tab, and new workflow conditions Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#%2804-February-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#%2804-February-2026%29 Wed, 04 Feb 2026 00:00:00 GMT Mend AI adds Open Beta support for AI Agents configuration, including discovery and risk assessment capabilities. • Introduces discovery, risk assessment, and workflow capabilities for AI Agents in the Mend AI platform (Open Beta). Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.12.1-%2805-January-2026%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.12.1-%2805-January-2026%29 Mon, 05 Jan 2026 00:00:00 GMT Mend AI 25.12.1 adds open beta System Prompt Risk detection and side panel. • Adds 'System Prompt Risk' detection to invent system prompts in conversational AI interfaces (open beta) • Adds 'System Prompt Risk' table with quick export/sharing and deep-link side panel for prompt context • Integrates System Prompt Risks into existing AI Security Risk Factors across Projects and Applications with a filterable 'Conversational Interface' chip • Enriches the AI Security Dashboard with system prompt risk data • Exposes system prompt risk data via API Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.9.1.2-%2805-October-2025%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.9.1.2-%2805-October-2025%29 Sun, 05 Oct 2025 00:00:00 GMT Mend AI 25.9.1.2 updates Behavioral Risks scores on the Overview page. • Redesigned the scores on the Overview page of the Behavioral Risks (Red-Teaming) Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.9.1.1-%2830-September-2025%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.9.1.1-%2830-September-2025%29 Tue, 30 Sep 2025 00:00:00 GMT Adds two new API endpoints for listing AI security findings by project or application • Introduces `GET /api/v3.0/projects/{projectUuid}/ai/model/findings/security` endpoint to retrieve AI model security findings for a specific project. • Introduces `GET /api/v3.0/applications/{applicationUuid}/ai/model/findings/security` endpoint to retrieve AI model security findings for a specific application. • Adds additional fields to the models endpoint in the Findings - Project API, aligning data with the "AI Models" page UI. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.9.1.1-%2830-September-2025%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.9.1.1-%2830-September-2025%29 Tue, 30 Sep 2025 00:00:00 GMT Mend AI 25.9.1.1 adds GET endpoints for listing AI security findings and expands model fields. • Adds `GET /api/v3.0/projects/{projectUuid}/ai/model/findings/security` endpoint to list AI security findings at the project level • Adds `GET /api/v3.0/applications/{applicationUuid}/ai/model/findings/security` endpoint to list AI security findings at the application level • Expands the models endpoint in the Findings - Project API with additional fields aligning with the 'AI Models' page Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.5.1-%2809-June-2025%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.5.1-%2809-June-2025%29 Mon, 09 Jun 2025 00:00:00 GMT Mend AI v25.5.1 adds configurable AI scanning toggles, CLI support for new settings, and license detection for top 100 open-source models. • Adds updated toggles for easier customization of AI scanning capabilities • Introduces intuitive labels and selective management options for AI features • Streamlines CLI support for new configuration settings controlling AI behavior • Enables detection of licenses for the top 100 open-source AI models with associated risk levels Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.5.1-%2809-June-2025%29 https://docs.mend.io/platform/latest/mend-ai-release-notes#Version-25.5.1-%2809-June-2025%29 Mon, 09 Jun 2025 00:00:00 GMT Mend AI 25.5.1 adds configurable AI scanning toggles and CLI support for license detection of top 100 open-source models • Enables detection of licenses for the top 100 open-source AI models, including license risk level details Full history on Cyber Toolchain: https://cybertoolchain.io/tools/mend-ai