paul-graham-perspective

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's 'Agentic Protocol' in SKILL.md creates a surface for indirect prompt injection by instructing the agent to gather data from external search results. However, the skill provides a multi-step reasoning framework including 'Checkpoint' self-tests and internal summarization steps that mitigate the risk of search results directly influencing the agent's behavior.
  • [COMMAND_EXECUTION]: The SKILL.md file includes instructions in the '版本自检 (静默)' section for the agent to execute local git commands (rev-parse and ls-remote) to check for skill updates. These commands are limited to the skill's own directory and serve a benign maintenance purpose.
  • [EXTERNAL_DOWNLOADS]: The README.md file recommends installing the skill using npx skills, which fetches content from the author's GitHub repository. This utilizes a standard deployment utility and represents legitimate software distribution within the platform's ecosystem.
  • [PROMPT_INJECTION]: The skill contains prescriptive role-playing instructions to ensure persona consistency and specifically warns against common 'hedging' behaviors. It follows security best practices for persona skills by providing a dedicated 'EXIT TRIGGER' in SKILL.md to allow users to return the agent to its default state.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 08:12 AM