cpp-api-abi-review
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a specialized workflow for C++ API and ABI analysis without incorporating any malicious commands, obfuscated content, or unauthorized access patterns.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted C++ source code as its primary function, creating an inherent surface for indirect prompt injection.\n
- Ingestion points: Reads C++ headers and diffs through file access as specified in the workflow.\n
- Boundary markers: Not present; the skill does not instruct the agent to use specific delimiters for code ingestion.\n
- Capability inventory: Limited to read-only file access; lacks network, write, or command execution tools.\n
- Sanitization: No content sanitization or filtering is defined for the processed source code.\n
- Risk: Potential for maliciously crafted C++ comments to influence agent behavior, though impact is limited by the lack of destructive capabilities.
Audit Metadata