technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and rewrite untrusted content including READMEs, RFCs, and PR descriptions.
- Ingestion points: The skill operates on external text data provided by the user or fetched from the repository context (e.g., SKILL.md, PR bodies).
- Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded prompts within the documents being reviewed.
- Capability inventory: The skill is configured to review and modify project documentation, which involves reading and potentially writing to the file system or responding to PRs.
- Sanitization: No sanitization or escaping mechanisms are defined for the content being processed.
Audit Metadata