prd-relations

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill follows best practices for document management tools, including human-in-the-loop confirmation before modifying any project files.
  • [DATA_EXPOSURE]: The skill reads local markdown files in the prd/ directory to extract requirements and dependencies. This data access is necessary for the skill's primary function and no data is transmitted externally.
  • [COMMAND_EXECUTION]: The skill uses agent-native file system operations to generate reports and update PRD files. It does not use system shells or execute arbitrary commands.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted user-provided PRD content, the risk of instruction injection is mitigated by the structured parsing logic and a mandatory manual review step before any automated fixes are applied to the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 08:55 AM