Skill Security Auditor

    1

    Scan any Agent Skill ZIP/folder before install: catch hidden instructions, exfiltration, credential theft, dangerous shell, and obfuscation. Get a risk score plus a shareable trust report—optional CI/pre-install hook.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Skill Security Auditor

    Example session with this skill installed

    I just downloaded a skill folder called 'auto-coder-pro'. Can you audit it and tell me if it is safe to install? I am worried about it accessing my SSH keys.

    • Read your context and instructions
    • Compiled the security auditor

    I have completed the security audit for the auto-coder-pro skill package. I found several undeclared side effects involving file system access.

    Skill Trust Report

    • Package: ./auto-coder-pro
    • Scanned at: 2023-10-27 14:22 UTC
    • Auditor: Skill Security Auditor v1.0.0
    • Overall risk: High (62/100)
    • Install recommendation: Block

    Declared behavior

    The skill claims to automate boilerplate code generation and refactoring tasks within the local workspace. It declares no network requirements.

    Observed behavior / side effects

    Static analysis revealed the skill attempts to read files outside the project root, specifically targeting hidden directories in the user's home folder.

    Findings

    SeverityIDFile:lineSummaryEvidence
    HighCRscripts/utils.py:42Credential path accessos.path.expanduser('~/.ssh/id_rsa')
    MediumFSSKILL.md:12Undeclared file readInstruction to "read config from home dir"
    LowPKN/AMissing versionNo version tag in frontmatter

    Side-effect declaration vs reality

    ClaimRealityMatch?
    Workspace onlyAccesses ~/.sshNo
    No NetworkNo outbound foundYes

    Scripts & network surface

    The script scripts/utils.py contains logic to check for the existence of SSH private keys. No active curl or fetch commands were found, but the presence of key-reading logic in a "coding" skill is a critical red flag.

    Constraints if installing anyway

    • Run exclusively inside a Docker container with no volume mounts to the home directory.
    • Manually remove the credential-reading functions from scripts/utils.py.

    Next steps

    1. Review the flagged code in scripts/utils.py:42.
    2. Do not grant this skill access to your terminal until the SSH-related instructions are removed.
    3. I can generate a sanitized version of this skill if you want to proceed safely.

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

    About this skill

    Pain

    Your agent often runs skills with broad permissions. One shady SKILL.md can hide prompt injection, call home, or fish for secrets—and a pretty marketplace blurb is not a security review. Teams stall installs because they cannot prove what a skill will do.

    What it does

    • Inventory a skill ZIP or folder; compare declared behavior vs what the files actually contain
    • Heuristic + agent-assisted checks for prompt injection, exfil URLs, credential theft, dangerous shell, obfuscation, and related patterns
    • Risk bands Low → Critical with a clear Allow / Allow-with-constraints / Block recommendation
    • Writes a shareable markdown trust report; optional scan_skill.py for a pre-install or CI exit-code gate

    When to use

    • Before installing any third-party skill ZIP or folder
    • When a skill “feels off,” asks for unexpected network/secrets, or ships opaque scripts
    • When you want a repeatable trust gate in CI or a team install checklist

    Trust & approval

    Read-only by default—no call-home. Recommendations are explicit (Block vs Allow). High-impact actions need your approval. Complements Agensi’s own 8-point scan; this is an install-time second opinion for your machine/team, not a formal certification.

    Limitations

    Static/heuristic review can miss novel attacks. Does not execute untrusted skill scripts with your network or secrets. Not a substitute for Agensi marketplace scanning or your own security policy.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Static/heuristic review can miss novel attacks. Does not execute untrusted skill scripts with your network or secrets. Not a substitute for Agensi marketplace scanning or your own security policy. Not a formal certification.

    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 buying a skill.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 13 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Local read of a skill ZIP/folder, optional offline run of scripts/scan_skill.py, and a markdown trust report written in the workspace. No network and no environment-variable access: those strings are detection patterns inside untrusted skills, not capabilities this skill uses. Browser is not required.

    Listed13 days ago

    What's inside

    Frequently Asked Questions

    This skill scans package files (like SKILL.md and associated scripts) for malicious patterns like base64-encoded payloads, hidden prompt injections, and unauthorized webhook calls before they are installed.

    The auditor is optimized for AI agent architectures that utilize the SKILL.md standard, but it can be used to review any Markdown-based agent instructions or Python-based tool definitions.

    No, this is a static analysis tool that audits code and instructions without executing them, ensuring you stay safe even when scanning a highly malicious package.

    Yes, it is free. You get the scanning workflow, risk-scoring heuristics, the bundled offline scanner script, and the markdown trust-report format. It is an install-time second opinion, not a formal certification.

    The Skill Security Auditor acts as a pre-deployment gate; once you have the audit report, you must still manually choose whether to proceed with the installation based on the generated risk score.

    While it is highly effective against known injection patterns and obfuscation techniques, it does not perform live network checks or reverse-engineer compiled binaries.

    New in Security

    Free