generate-agent-docs
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): The skill possesses an indirect prompt injection surface as it is designed to ingest and process external files (agents, skills, prompts). ● Ingestion points: Source files located in provider folders such as .github/, .claude/, .codex/, or .config/opencode/. ● Boundary markers: None specified in the instructions to prevent the model from following instructions embedded within the documented files. ● Capability inventory: Markdown generation and text processing only; no command execution or network capabilities. ● Sanitization: No sanitization or escaping mechanisms are mentioned.
- [No Code] (SAFE): The skill is composed entirely of markdown instructions and templates, containing no associated scripts, binaries, or automated execution logic.
Audit Metadata