doc-req-validator
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local scripts, specifically './ai_dev_ssd_flow/07_REQ/scripts/validate_req_template.sh' and 'ai_dev_ssd_flow/07_REQ/scripts/validate_req_spec_readiness.py', to perform automated structural and metadata checks on document artifacts. These scripts are located within the project's own directory structure.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it parses user-provided markdown files. 1. Ingestion points: The skill reads files from 'docs/07_REQ/'. 2. Boundary markers: None identified in the skill instructions. 3. Capability inventory: The agent is authorized to run local bash and Python validation scripts. 4. Sanitization: No explicit sanitization or escaping mechanisms for the ingested content are mentioned. This surface is considered safe because the scope of processing is limited to structural validation without external data exfiltration.
Audit Metadata