docs-audit-and-refresh

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's operations are consistent with its stated purpose of auditing and updating documentation. It performs local read/write operations within the repository's source and documentation folders.
  • [SAFE]: The skill accesses code, tests, and configuration surfaces to verify documentation accuracy. This is a functional requirement and does not involve unauthorized access to sensitive system files or external data transmission.
  • [PROMPT_INJECTION]: The skill processes repository content as part of the audit, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Source code and documentation files across various project directories (e.g., packages/cli, packages/core).
  • Boundary markers: No specific delimiters or safety instructions are defined to separate ingested content from the agent's instructions.
  • Capability inventory: The skill is authorized to update documentation files and navigation metadata (_meta.ts) within the docs/ directory.
  • Sanitization: No explicit validation or sanitization steps are mentioned for the content being ingested.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 09:50 PM