design-audit
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project files to perform the design audit, creating a surface for indirect instructions.
- Ingestion points: Project files are read using the uiux_scan_project tool as part of the scan project phase in SKILL.md.
- Boundary markers: The skill does not explicitly define markers to separate untrusted project content from agent instructions.
- Capability inventory: The skill performs file system scanning, agent-based analysis, and writes a report to design-audit-report.md.
- Sanitization: No specific sanitization or filtering of the ingested source code is mentioned.
Audit Metadata