docs
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the project's local file system, which may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: In the 'Find the docs first' step, the skill reads existing documentation pages from directories such as docs/, documentation/, or content/docs/ to match structure and frontmatter.
- Boundary markers: The skill does not define specific delimiters or 'ignore instructions' when processing the content of neighboring documentation files.
- Capability inventory: Across SKILL.md and README.md, the skill demonstrates the capability to create new documentation files, reorganize existing sections, and modify navigation or index files.
- Sanitization: No sanitization, validation, or filtering of the content read from external documentation files is specified in the skill instructions.
Audit Metadata