book-skill-creator

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes tools such as WebFetch and search to retrieve technical data from official documentation and technology websites for the purpose of skill planning.
  • [COMMAND_EXECUTION]: The skill defines a framework for environment setup using system-level commands in its templates and specifications, though current implementations are limited to benign operations like echo, mkdir, and chmod.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted external content (documentation and URLs) to generate plans and code for new skills. (Category 8: Indirect Ingestion).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 08:45 AM