to-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a documentation generator. Analysis of its instructions and template confirms it does not perform network exfiltration, execute arbitrary commands, or establish persistence.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local files and environment metadata, which could potentially contain malicious prompts. The risk is minimized by the skill's limited capabilities and explicit safety instructions.
- Ingestion points: The skill reads source code paths, error/log excerpts, and environment data (SKILL.md).
- Boundary markers: Summarization is constrained by a structured brief template (assets/brief-template.md).
- Capability inventory: The skill is restricted to writing Markdown files to the 'docs/prompts/' directory (SKILL.md).
- Sanitization: Instructions explicitly mandate the exclusion of credentials and unrelated private data (SKILL.md).
Audit Metadata