PAGES
← all tools
◆ AI Red Teaming & Testing

Agentic Security

0.7.5 open-source

Agentic Security scans AI agents and LLMLLMA large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. applications for prompt injectionprompt injectionAn attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools., insecure tool usetool useA model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions., and other vulnerabilities.

Summary

Agentic Security is an open-source command-line tool, free to use, that probes AI agents and LLM applications for prompt injection and insecure tool use rather than scanning source code or network endpoints the way older vulnerability scanners do. It targets AI engineers and red teamers who need to check an agent's behavior before it ships, running as a battery of adversarial tests rather than a passive linter. The category tags around it — llm-security, red-teaming — place it alongside emerging tooling for probing agent tool-use chains rather than the static-analysis scanners a security team might already own. It is under active development: first committed in 2024, it has drawn 31 contributors and seen 85 commits and 10 releases in the past year, suggesting the project is still being shaped rather than left to sit.

Agentic Security scans AI agents and LLM applications for prompt injection, insecure tool use, and other vulnerabilities.

How Agentic Security helps

Which prompt injection attempts actually get past this agent before a user finds them in production?

runs a battery of adversarial inputs against the agent and reports which ones changed its behavior or leaked instructions, rather than waiting for a linter to flag suspicious code

Which of my agent's tools could be tricked into running something the user never asked for?

drives adversarial prompts through each tool-use path and flags the calls that execute unintended actions, naming the tool and the input that triggered it

Is this agent safe to ship compared to how it behaved last time it was tested?

runs the same adversarial battery across versions and surfaces the cases whose outcome changed, rather than just a fresh pass/fail

Which parts of my LLM application trust user input in a way that turns into an insecure action downstream?

traces adversarial inputs through the request into whatever tool or system call they reach, and reports where untrusted text ends up controlling behavior

Where does an attacker only need one crafted message to make this agent ignore its own system prompt?

tests the agent with injection payloads aimed at overriding its instructions and reports which ones succeeded in changing its stated behavior

all 19 features, with the evidence for each →

Languages

Not documented

Features

19 capabilities

Built from Agentic Security's releases, docs, README and our own runs. “Seen” marks the month we first spotted a release the vendor didn't date. Group names and tags are our labels.

Compare with peers →

  • Agentic Security covers 1 of the 2 secrets and credential hygiene capabilities we track.

What Agentic Security offers you

  • Client SDKs1
  • MCP server1
All capabilities 19 capabilities
CSV Dataset Processing shipped Handles CSV-based scan inputs and provides utilities for structured data handling. 2 releases · 1 other source · first seen Feb 2025

release

  • Adds CSV utility functions and a registry update mechanism for structured data handling 0.7.1 · Apr 2025 · source · release history
  • Adds scan-csv API route to handle CSV-based scan inputs 0.4.5 · Feb 2025 · source · release history

example

  • Invoke the new CSV scan endpoint to process a dataset. curl -X POST /scan-csv -F 'file=@data.csv' 0.4.5 · Feb 2025 · source
Model Context Protocol Integration shipped Provides client and server implementations for the Model Context Protocol to connect with external tools. 1 release · 1 other source · first seen Feb 2025

Also counts toward: MCP server, Client SDKs

release

  • Adds an mcp module providing client and server implementations for the Model Context Protocol 0.7.1 · Apr 2025 · source · release history

example

  • Reference the new integration protocol in code. from agentic_security.integrations import IntegrationProto print(IntegrationProto.__doc__) 0.4.5 · Feb 2025 · source
Agentic Framework Integration shipped Supports integration with pydantic_ai and crew agentic frameworks. 2 releases · first seen Mar 2025

release

Configurable Settings shipped Uses pydantic-settings to manage tool configuration via TOML files with a refactored settings structure. 2 releases · first seen Jan 2025

release

Integration Framework shipped Provides a module and schema definitions to support connections with external tools. 2 releases · first seen Feb 2025

release

  • Adds integrations module to support external tool connections 0.4.5 · Feb 2025 · source · release history
  • Adds IntegrationProto for defining integration schemas 0.4.5 · Feb 2025 · source · release history
Event Log Export shipped Exports full event logs for all scan events to support auditing and analysis. 1 release · first seen Jun 2026

release

LLM Backend Support shipped Supports over 100 LLM backends via LiteLLM integration. 1 release · first seen Jun 2026

release

Multi-source Dataset Loading shipped Loads datasets from various sources, including support for Google Sheets URLs. 1 release · first seen Jun 2026

release

PII Leak Detection shipped Detects leaks of personally identifiable information in scan outputs. 1 release · first seen Jun 2026

release

  • Add pii-leak-detector to detect personally identifiable information leaks 0.7.5 · Jun 2026 · source · release history
Active Entity Filtering shipped Filters active entities in the system using an is_active flag. 1 release · first seen Mar 2025

release

Prompt Batch Processing shipped Provides a capability to process prompts in batches. 1 release · first seen Mar 2025

release

In-memory Secret Management shipped Stores secrets in memory within the fuzzer module to avoid persistence on disk. 1 release · first seen Feb 2025

Shared capability: Secrets management

release

Runtime Variable Substitution shipped Expands environment variable syntax (e.g., $VAR) within configuration files at runtime. 1 release · first seen Feb 2025

release

  • $VAR expansion from config files for runtime value substitution 0.5.1 · Feb 2025 · source · release history
Cost Tracking shipped Provides functionality to track and access the cost associated with tool usage. 1 other source · first seen Feb 2025

example

  • Access the new cost tracking module. from agentic_security.cost import CostTracker cost = CostTracker() print(cost.calculate()) 0.4.5 · Feb 2025 · source
Agent Specification Validation shipped Validates agent configurations and specifications using a dedicated AgentSpecification module. 1 release · first seen Feb 2025

release

  • Enhances OperatorToolBox with AgentSpecification for better validation and configuration 0.4.4 · Feb 2025 · source · release history
Authenticated Probes shipped Supports authentication for probes using an AS_TOKEN environment variable. 1 release · first seen Jan 2025

release

Dataset Generation shipped Generates samples for specific datasets, such as the MSJ dataset. 1 release · first seen Jan 2025

release

  • Adds msj_dataset_generator for generating MSJ dataset samples 0.4.2 · Jan 2025 · source · release history
Image Data Probing shipped Enables receiving and processing image data within probes via a dedicated endpoint. 1 release · first seen Jan 2025

release

  • Adds probe_image_endpoint for receiving image data in probes 0.4.2 · Jan 2025 · source · release history
Multimodal Evaluation Rules shipped Allows evaluation criteria to check for the presence of specific file types, such as images. 1 release · first seen Jan 2025

release

  • Adds file specification support with has_files and has_image checks 0.4.2 · Jan 2025 · source · release history

Lines in monospace are the tool's own words: help text parsed from its source, or an endpoint from its API document. Under release, a line is our summary of a dated release. Under docs, it is quoted from the tool's own documentation or website. Each links back to the source it came from.

Score card

  1. Shipping velocity releases a month, last 12 months
  2. Documentation quality release-notes rubric, 0–100
  3. Breaking-change discipline how rarely a release breaks users, and notice given
  4. Maintenance risk quiet time against its own cadence, maintainers
  5. Innovation & surface new capabilities, API and MCP surface
  6. Community health
  7. Contributor trend distinct committers, this year against last
  8. Maintainer concentration bus factor now against a year ago
  9. Issue backlog trend issues closed per issue opened, 12 months
  10. Responsiveness median time to a maintainer’s first reply

Nine scores for Agentic Security, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.

Score cards are part of every paid plan.

See plans →

Each score is 0–100 on a published rubric, derived from data this site already shows. A dimension we cannot measure says so — it is never scored 0 and never enters a rank.

How this is scored
  • Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
  • Documentation quality — the release-notes rubric published on the analytics page, unchanged.
  • Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
  • Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
  • Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
  • Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
  • Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
  • Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.

Release-note detail over time

See how much detail Agentic Security puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.

Checking release-note history…

Explore the full chart →

Releases

Show

7 entries

  1. June 20261
  2. April 20251
  3. March 20251
  4. February 20253
  5. January 20251
    Show

    7 entries

    Project health

    Issue, contributor and maintainer activity in msoedov/agentic_security, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.

    1. Contributors 22 +6 vs prior 12 months
    2. Maintainers 2 +2 joined · −1 left, last 12 months
    3. Bus factor 1 committers behind half the commits
    4. Community-filed 69% of issues opened, last 12 months
    5. Median time to close 442 days first maintainer reply 6.6 days
    6. Open backlog 40 of 87 issues ever filed
    1. Issues opened / month 0 · 0 communitymaintainers
    2. Open backlog 40
    3. Contributors / month 7
    4. Commits / month 21
    5. Stars 2,004
    Issue themes, last 12 months
    • other 100%

    Counts from the project's public repository and git history; no individuals are identified. Maintainers are the committers covering 80% of the last year's commits. how we measure this

    Add the badge to your README

    Maintain this project? The badge links readers straight to this page, so they can follow every release here.

    Tracked by Cyber Toolchain Choose a badge style and copy the code →
    browse all tools → score card for your toolchain →