patent-drafter

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided technical invention details which are passed across multiple agents and used to generate files.
  • Ingestion points: User input extracted during Phase 1 (Preparation) including Title of Invention, Technical Field, and Invention Overview in skill.md.
  • Boundary markers: None explicitly defined in the workflow to separate user content from agent instructions.
  • Capability inventory: File system write access (_workspace/ directory) and inter-agent communication (SendMessage) throughout the workflow.
  • Sanitization: No input validation or sanitization of technical descriptions is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 04:21 AM
Security Audit — agent-trust-hub — patent-drafter