wiki-page-writer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were detected in the skill instructions. The skill correctly scopes its operations to documentation generation and analysis of provided files. The instructions encourage evidence-based documentation and citations, which promotes transparency and verification.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code to generate documentation, which is a standard surface for indirect prompt injection.
- Ingestion points: Implementation analysis step in
SKILL.mdrequiring the agent to "Read all relevant files". - Boundary markers: None explicitly defined to separate code content from instructions, though the output format (VitePress/Markdown) acts as a natural separator.
- Capability inventory: File reading for analysis purposes is the primary capability. The skill does not request file-writing, network access, or shell execution permissions.
- Sanitization: No explicit sanitization of input files is performed, as the agent is expected to interpret the code as-is for documentation purposes.
Audit Metadata