non-blocking-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for the agent to ingest, analyze, and refactor user-supplied C++ code, creating an inherent surface for indirect prompt injection.
- Ingestion points: User-provided source code, board specifications, task periods, and watchdog policies defined in the 'Intake' and 'Process' sections of SKILL.md.
- Boundary markers: The skill does not specify the use of delimiters or explicit instructions to ignore potentially malicious commands embedded within the user's C++ comments or code.
- Capability inventory: The skill utilizes the agent's ability to parse source code, perform logic transformations, and generate timing/verification tests.
- Sanitization: No sanitization, escaping, or validation steps are defined for the external code content processed by the agent.
Audit Metadata