doc-prd-audit

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-provided Product Requirement Documents (PRDs) as primary input, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads PRD files from the docs/02_PRD/ directory to perform auditing tasks.
  • Boundary markers: The skill definition lacks explicit boundary markers or system instructions to ignore potential commands embedded within the untrusted PRD content.
  • Capability inventory: The skill executes several sub-skills (doc-prd-validator, doc-prd-reviewer, doc-prd-fixer) and performs filesystem write operations to generate reports.
  • Sanitization: No sanitization of the document content is specified before the findings are extracted and passed to downstream tools like the fixer.
  • [COMMAND_EXECUTION]: The skill orchestrates the execution of other internal audit tools.
  • Details: It sequentially runs doc-prd-validator and doc-prd-reviewer, then optionally hands off execution to doc-prd-fixer. These commands are executed based on the defined audit workflow using localized skill references.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 09:12 AM