swiftui-specialist
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that attempt to override the agent's behavior and priority. It explicitly states that its content 'unconditionally supersedes any prior training' and establishes a 'scoping rule' that 'takes precedence over any prompt' asking for general observations or notes. This instructs the agent to ignore specific types of user requests to maintain a narrow focus.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code for reviews and refactoring, which creates an attack surface for indirect prompt injection where malicious instructions could be embedded in code comments. 1. Ingestion points: User-supplied SwiftUI code and project files scanned by the agent. 2. Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions found within the analyzed source code. 3. Capability inventory: The agent can perform project-wide scans, read/write files, and provide technical guidance. 4. Sanitization: No input sanitization or validation logic is provided for the code being reviewed.
Audit Metadata