More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Skill Antivirus

    1

    Security review tool for agent skills using static analysis and LLM heuristics to detect malicious content.

    Free

    1 useSecurity scanned
    Skill Antivirus

    Skill Antivirus

    Example session with this skill installed

    Scan this community skill ZIP at ./downloads/useful-skill.zip and give me a security verdict.

    • Read your context and instructions
    • Compiled the antivirus

    Verdict: REVIEW. Static analysis found one .exe file (executable-payload). LLM review of SKILL.md flagged a suspicious instruction to read ~/.ssh/config. Recommendation: Use classic AV on the binary.

    found one .exe file (executable-payload). LLM review of SKILL.md

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

    About this skill

    The problem

    Third-party AI agent skills can contain prompt injections, malicious scripts, or exfiltration triggers. Running these packages without a security audit risks compromising your environment and secrets.

    What it does

    • Performs deterministic static analysis on directories and ZIP packages to find known threats and hazardous file types.
    • Executes an LLM heuristic review of every text-readable file to judge intent against a security taxonomy.
    • Stages ZIP files in a read-only temp directory with path-safe extraction to prevent directory traversal or execution during review.
    • Generates structured JSON and human-readable reports with specific verdicts: CLEAN, REVIEW, or UNSAFE.

    Frameworks & tools

    Python-based static analysis, LLM-based heuristic review, and a structured security taxonomy.

    Why this beats prompting it yourself

    Manual review often misses hidden payloads in assets or nested scripts. This tool enforces a strict containment protocol, ensuring the reviewing agent never executes the hostile code or follows instructions inside the scanned package.

    Use cases

    • Auditing a community-contributed skill ZIP before installation.
    • Performing a pre-publish hygiene check on your own agent tools.
    • Scanning SKILL.md files for prompt injection or unauthorized network call instructions.

    Known limitations

    This is an advisory tool and not a guarantee of safety. It does not replace classic antivirus for native executables and does not execute content to observe runtime behavior.

    Does not guarantee malware absence. Requires user consent for external binary scanning. Does not observe runtime behavior.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Virustotal
    Node.js
    Python

    Permissions

    Terminal / Shell
    Network Access

    Allowed Hosts

    www.virustotal.com
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill scans third-party packages for prompt injections, malicious scripts, and data exfiltration triggers by combining traditional static code analysis with AI-driven intent heuristics.

    The tool supports directory structures and ZIP packages commonly used in AI agent marketplaces, specifically scanning text-based files, configuration manifests, and SKILL.md documentation.

    Safety is ensured by staging files in a read-only temporary directory with path-safe extraction, preventing the analysis process from accidentally triggering directory traversal or executing code.

    No, this is an advisory tool that performs static and heuristic analysis; it does not execute code in a sandbox or monitor runtime behavior once the agent is live.

    You will receive the complete Python-based security tool, the proprietary security taxonomy used for grading threats, and the ability to generate both structured JSON and human-readable audit reports.

    Yes, this skill is designed to be framework-agnostic, making it suitable for auditing skills intended for AutoGPT, LangChain, CrewAI, or any custom Python-based agent environment.

    New in Security