c-pro
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and implement user-supplied C source code, which serves as an entry point for indirect prompt injection attacks.
- Ingestion points: User-provided code via implementation and review requests (SKILL.md).
- Boundary markers: Absent; the skill does not instruct the agent to use delimiters or safety markers for ingested code.
- Capability inventory: The skill utilizes code generation, static analysis (clang-tidy), and debugging tools (valgrind, gdb) when supported by the environment.
- Sanitization: Absent; there are no requirements for escaping or validating input code before it is processed by the agent.
Audit Metadata