design-orchestration

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user input in the form of feature proposals or system changes to determine routing between design agents. This creates a surface for indirect prompt injection where a user could provide instructions to bypass risk assessments or de-escalate required reviews.
  • Ingestion points: Processes user proposals for new features or systems (SKILL.md under 'Entry Conditions').
  • Boundary markers: No explicit delimiters or 'ignore' instructions for the external content are defined in the orchestration logic.
  • Capability inventory: Manages invocation of brainstorming and multi-agent-brainstorming skills; enforces workflow constraints.
  • Sanitization: No explicit sanitization or validation of the input content is implemented within the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:35 AM
Security Audit — agent-trust-hub — design-orchestration