to-prd

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No security threats detected. The skill is purely instructional and contains no associated scripts or executables.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes repository data and conversation history to generate text specifications. While this allows for potential data ingestion from untrusted sources, the impact is confined to document generation. 1. Ingestion points: Current conversation and repository files such as ADRs and glossary (SKILL.md). 2. Boundary markers: None. 3. Capability inventory: Publishing to a detected issue tracker (SKILL.md). 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:15 PM
Security Audit — agent-trust-hub — to-prd