llm-wiki-repo-docs
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructions and guidelines for documentation maintenance. It does not perform any network operations, download external code, or request elevated system privileges.- [DATA_EXPOSURE]: The skill includes specific safety gates that instruct the agent to avoid placing secrets or internal URLs into documentation that may be broadly readable.- [PROMPT_INJECTION]: The skill uses repository data to build documentation, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests repository path contents, existing READMEs, ADRs, and package manifests.
- Boundary markers: The instructions do not define specific delimiters for separating ingested content from the agent's internal logic.
- Capability inventory: The agent is authorized to write markdown files to the repository filesystem (specifically in wiki/ or docs/ directories).
- Sanitization: The skill includes a safety requirement to re-verify descriptions against source files before publishing, which provides a verification loop to check for drift or inaccuracies introduced by external data.
Audit Metadata