design-orchestration

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-proposed features and design documents, serving as an ingestion point for untrusted data that could attempt to manipulate the risk assessment or approval logic. * Ingestion points: User-proposed features, system changes, and design artifacts referenced in SKILL.md. * Boundary markers: No delimiters or explicit instructions are provided to separate user content from the orchestration logic. * Capability inventory: The skill coordinates work through brainstorming and review skills and controls the transition to implementation planning. * Sanitization: No validation or filtering of incoming design content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:04 PM
Security Audit — agent-trust-hub — design-orchestration