afk-code-review-check
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes output from an external tool (
afk-code-review) which analyzes potentially untrusted source code. This creates a risk where instructions embedded in the reviewed code could attempt to influence the agent's behavior via the tool's findings. - Ingestion points: The agent is instructed to capture and present the complete output from the
afk-code-reviewtool as specified inSKILL.md. - Boundary markers: The prompt uses a
## Verified verdictsheader to distinguish between the external tool's raw output and the agent's subsequent analysis. - Capability inventory: The agent has the capability to read and potentially modify local source code files based on the context of code review.
- Sanitization: The instructions mandate a manual verification process, requiring the agent to inspect code evidence and confirm findings against the actual source code before making changes, which serves as a logic-based sanitization step.
Audit Metadata