prd-clarifier

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection. By reading and 'analyzing' untrusted PRD files, the agent could be manipulated by malicious instructions hidden within those documents.
  • Ingestion points: The skill explicitly reads PRD files from the user's directory (Step 1).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the PRD content as untrusted data.
  • Capability inventory: The skill has the capability to write and update markdown files (tracking documents) in the local file system.
  • Sanitization: The skill does not perform any validation or sanitization on the content extracted from the PRD files before using it to drive the questioning strategy.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM