research

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external web sources, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through mcp__web-search-prime__webSearchPrime, mcp__web-reader__webReader, and native WebFetch tools (SKILL.md).
  • Boundary markers: The skill lacks explicit instructions or markers to distinguish between trusted instructions and untrusted content fetched from the web.
  • Capability inventory: The skill includes tools for fetching repository data (mcp__web-search__fetchGithubReadme) and articles from various platforms like GitHub, CSDN, and Juejin (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering applied to the retrieved content before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 11:06 AM
Security Audit — agent-trust-hub — research