prd
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from
.claude/reference/PRD.mdto generate task plans, updates, and validation reports. In plan mode, it specifically extracts test file mappings to generate verification commands (e.g., npx vitest). - Ingestion points: The skill reads
.claude/reference/PRD.mdacross multiple modes (Plan, Update, Validate, Audit) and scans the codebase via an automated Explore agent. - Boundary markers: Absent; the instructions do not define delimiters or specific safety warnings to ignore instructions embedded within the PRD content during processing.
- Capability inventory: The skill possesses the capability to execute shell commands via npx, pnpm, and npm, and it performs file write operations to the
docs/plans/directory. - Sanitization: Absent; there is no evidence of validation or sanitization for the content extracted from the PRD before it is interpolated into task plan commands or markdown reports.
Audit Metadata