native-platform-porting
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard software engineering guidance for porting legacy code, focusing on Hardware Abstraction Layers (HALs) and refactoring hardware-coupled logic into native abstractions.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves processing untrusted legacy source code, which is a standard surface for coding-related tasks. It manages this risk by recommending sanitization and verification tools.\n
- Ingestion points: Legacy source code files and proprietary hardware SDK headers.\n
- Boundary markers: No specific delimiters are defined to separate user code from agent instructions.\n
- Capability inventory: The agent is guided to refactor, compile, and execute the resulting code for verification.\n
- Sanitization: The instructions include the use of compiler flags (-Wall, /W4) and diagnostic tools such as AddressSanitizer (ASan) and UndefinedBehaviorSanitizer (UBSan).
Audit Metadata