wiki-page-writer
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill executes
git remote get-url originandgit rev-parse --abbrev-ref HEAD. These are standard, safe commands used to resolve the repository context for generating accurate citation links. - [DATA_EXPOSURE] (SAFE): The skill reads local repository files to trace code paths and identify implementation details. This behavior is the intended primary purpose of the documentation generator.
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted local data (source code) to generate documentation, creating a potential surface for indirect prompt injection.
- Ingestion points: Local source code files throughout the repository as specified in the 'Analyze' step of SKILL.md.
- Boundary markers: Absent. The skill does not explicitly use delimiters or guardrail instructions when processing file content.
- Capability inventory: File system read access, git metadata retrieval, and markdown file writing.
- Sanitization: Absent. The skill processes and reflects implementation details directly into the documentation output.
Audit Metadata