validation-coordinator

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes implementation artifacts to guide its coordination workflow.
  • Ingestion points: The skill loads feature PRP documents and implementation files from the local filesystem (e.g., /docs/implementation/prp/feature-{issue-number}-prp.md).
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified for the ingested content.
  • Capability inventory: The skill is granted Bash and Read access and is responsible for invoking multiple validation specialists.
  • Sanitization: No evidence of input validation or sanitization is provided for the content retrieved from artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 09:11 PM