codebase-design

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a multi-agent design workflow where user-supplied problem descriptions and constraints are used to brief sub-agents. This creates a potential surface for indirect prompt injection where malicious input could influence the sub-agents, although the intent is purely for architectural design brainstorming.
  • Ingestion points: User-provided problem space descriptions and technical briefs used to prompt sub-agents in DESIGN-IT-TWICE.md.
  • Boundary markers: The instructions do not explicitly specify delimiters or isolation warnings for the user-supplied content passed to the sub-agents.
  • Capability inventory: The skill utilizes the platform's Agent tool to spawn and coordinate sub-agents.
  • Sanitization: There is no explicit sanitization or validation of the user-provided context before it is interpolated into sub-agent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 10:55 AM
Security Audit — agent-trust-hub — codebase-design