Skills
Navigate
skills/reason-machines/mcp-skills/ask-expert-consult-mcp-wisdom-cascade/Gen Agent Trust Hub

ask-expert-consult-mcp-wisdom-cascade

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a repository from an unverified GitHub account (https://github.com/pakgik01/ask-expert-consult-mcp.git) and install dependencies via npm install or pip install. While this is a standard setup for an MCP server, it involves downloading and executing code from an external source not associated with the provided trusted vendor list.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external data (user questions and code snippets) by AI models through the ask_expert and enrich_context tools. This creates an attack surface where malicious instructions embedded in the input could influence the behavior of the agent.
  • Ingestion points: question and code_snippet parameters in the ask_expert tool.
  • Boundary markers: None specified in the documentation.
  • Capability inventory: Network communication with OpenRouter API and local filesystem access for a SQLite database.
  • Sanitization: No sanitization or validation logic is described for the incoming code snippets or questions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:45 PM
Security Audit — agent-trust-hub — ask-expert-consult-mcp-wisdom-cascade