doc-req-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill performs automated document review and quality checks within a local project environment. It does not perform network operations, access sensitive credentials, or download external content.- [COMMAND_EXECUTION]: Uses standard Unix utilities (
sha256sum,cut,grep) to calculate and verify document hashes for a drift detection cache (.drift_cache.json). These commands are restricted to the local filesystem and are used for integrity verification purposes.- [PROMPT_INJECTION]: The skill ingests user-controlled data from REQ and SYS documents. 1. Ingestion points:docs/07_REQ/anddocs/06_SYS/directories. 2. Boundary markers: Not explicitly defined beyond standard Markdown formatting. 3. Capability inventory: File read/write access and local shell execution (sha256sum,grep). 4. Sanitization: Not specified for analyzed content. While this creates an ingestion surface for indirect prompt injection, the skill's logic is focused on structural and metadata validation rather than executing instructions within the documents.
Audit Metadata