uikit-expert
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to review and improve user-supplied UIKit code, creating an attack surface where malicious instructions could be embedded in the code being analyzed.
- Ingestion points: User-provided Swift source code, projects, and UIKit snippets analyzed in the
ReviewandImproveworkflows. - Boundary markers: The skill does not define specific delimiters or "ignore previous instructions" safety markers to be used when the agent processes external code.
- Capability inventory: The skill leverages the agent's code analysis and modification capabilities across a broad technical scope defined in 16 reference files.
- Sanitization: No explicit sanitization or validation logic is defined for the input source code to mitigate prompt injection risks.
Audit Metadata