doc-prd-validator
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides commands to execute local bash and Python validation scripts (e.g.,
prd_core_wrapper_hook.sh,validate_prd.py) located within the repository'sai_dev_ssd_flowdirectory.\n- [PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection as it is designed to ingest and validate externally authored PRD documents.\n - Ingestion points: PRD markdown files located in
docs/02_PRD/.\n - Boundary markers: The skill instructions do not explicitly provide delimiters or 'ignore embedded instructions' warnings for the data being validated.\n
- Capability inventory: The skill possesses the capability to execute shell and Python scripts for validation and auto-fix actions.\n
- Sanitization: While the skill enforces structural and metadata schemas, there is no mention of escaping or sanitizing the document content before it is processed by the agent.
Audit Metadata