design-critique
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the local codebase to generate design critiques, which presents a surface for instructions embedded in source files to influence agent behavior.
- Ingestion points: As described in Phase 1, the skill reads project configuration files (package.json, pubspec.yaml), styling definitions (CSS, design tokens), and component source code files.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or specific warnings to ignore instructions that might be embedded in the code or comments of the analyzed files.
- Capability inventory: The skill is defined as read-only. It possesses no capabilities for network exfiltration, file system modification, or shell command execution.
- Sanitization: Absent. There is no mention of sanitizing or escaping the content extracted from the codebase before it is analyzed or included in the final markdown report.
Audit Metadata