porting-discover

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to process and analyze external artifacts such as source code and RenderDoc XML captures.
  • This creates a potential surface where malformed input data could attempt to influence the agent's reporting or analysis logic.
  • The skill focuses on analysis only and does not include automated execution of the code being analyzed, which limits the potential impact.
  • System Utility Invocation: The skill utilizes standard system tools for performance analysis and process management.
  • Instructions include using ps to identify process IDs and xcrun xctrace to record performance data.
  • It also mentions leaks and vmmap for memory profiling, and codesign for binary signing, which are standard components of the macOS developer toolchain used for their intended purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:39 AM