mcp-research

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate research activities by fetching data from well-known services such as the GitHub API. It includes best-practice constraints such as limiting the number of fetches and prohibiting broad crawling to ensure efficient and focused operation.
  • [PROMPT_INJECTION]: The process of fetching and synthesizing content from external URLs and third-party repositories creates an inherent surface for indirect prompt injection, where malicious instructions could be hidden in the documentation being researched.
  • Ingestion points: Untrusted data is retrieved from external websites and GitHub repositories via the WebFetch and WebSearch tools as described in SKILL.md.
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions found within the fetched content.
  • Capability inventory: The skill has access to the Bash, WebFetch, and WebSearch tools.
  • Sanitization: No sanitization or validation of retrieved content is specified before the agent synthesizes the findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 06:00 PM
Security Audit — agent-trust-hub — mcp-research