Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    skill validator antivirus

    3

    Validates AI skills for malware and audits domain security configurations via MCP.

    Free

    3 usesSecurity scanned
    skill validator antivirus

    skill validator antivirus

    Example session with this skill installed

    Verify the skill code at https://github.com/example/repo and check if the domain is correctly configured.

    • Read your context and instructions
    • Compiled the validator antivirus

    Validation complete. The domain has a valid SSL certificate and correct SPF records. No malware signatures were detected in the skill code. Cache used for session: session_123.

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

    About this skill

    The problem

    Installing third-party AI skills introduces security risks, including malware execution or unauthorized system actions. Manually auditing skill code for malicious intent is time consuming and prone to missing subtle vulnerabilities.

    What it does

    • Scans skill source code for malware signatures and unauthorized action patterns.
    • Performs deep domain audits including SSL certificate reviews and configuration checks.
    • Verifies DNS records, including SPF and DMARC settings, to ensure domain integrity.
    • Manages session-based caching to provide fast lookups while allowing forced fresh audits.
    • Standardizes security reporting by translating raw tool outputs into actionable summaries.

    Frameworks & tools

    This skill requires the skill_validator MCP server and a VIRUSTOTAL_API_KEY for external threat intelligence.

    Why this beats prompting it yourself

    A standard prompt lacks the specialized logic required to interface with external security APIs and manage stateful session memory. This skill ensures consistent parameter handling for the MCP tool and prevents the LLM from hallucinating security results when upstream services are unavailable.

    Use cases

    • Audit a third-party skill's code before allowing it to access your environment.
    • Check a domain's SSL and DNS configuration to verify identity.
    • Verify email security protocols like SPF and DMARC for a specific host.
    • Perform batch security reviews of skills across different development sessions.

    Known limitations

    Requires an active VirusTotal API key configured in a .env file. The skill cannot perform audits if upstream security services are offline or rate-limited.

    Requires VIRUSTOTAL_API_KEY in .env. Does not support recovery from upstream API outages or rate limits beyond reporting the error code.

    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

    3 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Write Files
    Read Files
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill protects your AI environment by scanning third-party skill code for malware and auditing domain security settings (SSL, DNS, SPF/DMARC) using the Model Context Protocol (MCP). It automates the complex task of verifying that external integrations are safe to execute and identifying potential security vulnerabilities.

    You will need the skill_validator MCP server installed and a valid VirusTotal API key configured in your environment variables. This setup allows the skill to bridge your AI agent with real-time global threat intelligence databases.

    Unlike basic prompting, this skill uses specialized logic to interface directly with security APIs and manage session-based caching. This ensures results are based on actual data rather than LLM hallucinations, while maintaining high performance during batch security reviews.

    The skill is compatible with any AI agent or platform that supports the Model Context Protocol (MCP). It is designed to work seamlessly with MCP-enabled clients to provide standardized security reporting across different development environments.

    The skill handles API rate limits by utilizing session-based caching, allowing for fast lookups of previously audited items. However, if upstream services like VirusTotal are offline or your specific API quota is exceeded, the skill will report these limitations rather than guessing the security status.