prd-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes 'python3 plugins/testany-eng/scripts/trace_lint.py' to perform automated metadata validation. This script is a functional component provided by the author (testany-io) to ensure PRD compliance with established schemas.
- [PROMPT_INJECTION]: The skill's ingestion of user-provided PRD documents creates a surface for indirect prompt injection. (1) Ingestion points: PRD file content read from a user-specified path or pasted directly in SKILL.md. (2) Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are implemented in the prompt. (3) Capability inventory: The agent has permissions to read local files and execute a specific local Python script. (4) Sanitization: No explicit sanitization or validation of the input content is described before the analysis phase.
Audit Metadata