mao-zedong-perspective

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions guide the agent to use shell commands such as echo and grep to locate and search a local knowledge base. These commands are used to discover the path of a user-cloned repository and retrieve specific text references based on user queries.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by reading external text files from a local directory (MaoZeDongAnthology). This is an intended feature to provide the agent with a source for accurate quotes, though it relies on the integrity of the user-cloned content.
  • [EXTERNAL_DOWNLOADS]: The README provides instructions for the user to clone an optional knowledge base from a third-party GitHub repository. This download is managed by the user outside of the skill's automated execution and is clearly documented for providing context to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 12:16 PM
Security Audit — agent-trust-hub — mao-zedong-perspective