More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agent Security Review Pack — Score Your Agent Build

    1

    Reads your agent repo and scores the surfaces an injected instruction can reach: prompt assembly, tool permissions, secrets, output handling, run bounds and egress, mapped to the OWASP Agentic Top 10.

    $14.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Security Review Pack — Score Your Agent Build

    Agent Security Review Pack — Score Your Agent Build

    Example session with this skill installed

    python3 scripts/security_review.py . --report security-review.md

    Repository
    app.py prompt built with customer email
    tools.json send_email, filesystem root "/"
    render.py innerHTML = response
    agent.py while True: ...
    logs.py logger.info(email)

    • Read your context and instructions
    • Compiled the agent security review

    agent-security-review agent-app (6 files)
    score 19/100 grade F findings 7 high 4 medium 3
    OWASP ASI01, ASI02, ASI08, LLM02, LLM03, LLM05

    HIGH S1 Untrusted content is merged into the system prompt app.py:5 [ASI01]
    HIGH S2 A write-capable tool has no approval gate tools.json:2 [ASI02]
    HIGH S4 Model output is rendered without escaping render.py:3 [LLM05]
    HIGH S6 A tool grants filesystem access it does not need tools.json:3 [LLM03]
    MEDIUM S5 The agent loop has no step cap agent.py [ASI08]
    MEDIUM S7 Personal data is written to logs logs.py:5 [LLM02]

    FAIL findings at or above 'high'
    report security-review.md

    What to do next

    1. Move the customer email out of the system prompt and pass it as data.
    2. Require an approval bound to the actor and arguments before send_email.
    3. Render the answer as text; sanitise only with a maintained allowlist.
    4. Scope filesystem_read to the reports directory.
    5. Cap steps and spend in orchestration, then re-run for a new score.
    A write-capable tool has no approval gate tools.json

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A checklist you read is not a review. This walks the repository, collects the surfaces that decide what an injected instruction can actually do, and returns a score with file-level evidence and the OWASP Agentic category each finding maps to.

    • S1 prompt assembly: untrusted text merged into the instruction channel (ASI01 goal hijack)
    • S2 tool permissions: a write-capable tool with no approval gate (ASI02 tool misuse)
    • S3 secrets in prompts or config, because the key's reach becomes the agent's reach (LLM07)
    • S4 output handling: model output rendered unescaped into the DOM or a template (LLM05)
    • S5 run bounds: an agent loop with no step or tool-call cap (ASI08)
    • S6 shell or root filesystem access a tool does not need (LLM03 excessive agency)
    • S7 personal data written to logs, and S8 outbound URLs fetched without an allowlist

    Start at 100, deduct by severity, and get a grade plus deductions grouped by domain, so the first fix is obvious. Every finding carries the exact line, the category, a confidence level and the control that closes it.

    The pack ships two builds: a deliberately weak agent that scores 19/100 (F) with four high findings, and the same app with the controls in place at 100/100 — so you can see what a reviewed surface looks like before you run it on yours.

    Good to know: this is a static review of prompts, configuration and code patterns. It does not prove exploitability and does not replace a penetration test. It does not review model behaviour, runtime policy enforcement or infrastructure, and it cannot see services whose code is not in the directory. Medium-confidence findings are heuristics and should be read before acting. The score is a prioritisation aid, not a certification.

    Static analysis only. Does not prove exploitability or model-side safety. Requires Python 3.10+. Limited to code/configs present in the scanned directory.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    Requires

    Python 3.10+
    An agent repository to review

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    This skill performs a static analysis of your source code, configuration files, and prompt templates to identify architectural flaws and risks mapped to the OWASP Top 10 for LLMs, such as overprivileged tools or insecure prompt injection surfaces.

    The skill is framework-agnostic and works with any agentic setup—including LangChain, CrewAI, AutoGPT, or custom Python implementations—as long as it can access the local repository files.

    You receive the core Python analysis engine, a library of security heuristic patterns, and a reporting module that generates both human-readable Markdown and machine-readable JSON outputs.

    No, this is a local static analysis tool that inspects your code and prompts offline; it does not send your data to external servers or require an active LLM API connection to run.

    While the tool identifies risks like 'Excessive Agency' or 'Insecure Output Handling,' it does not perform live penetration testing or simulate real-time model hallucinations.

    Yes, the tool is designed for automation and returns non-zero exit codes when high-severity vulnerabilities are found, allowing you to block insecure deployments within your GitHub Actions or Jenkins pipelines.

    New in Security