grill-for-implementation
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No evidence of malicious patterns, such as prompt injection, obfuscation, or persistence mechanisms, was found. The skill consists of instructions for engineering design review.
- [DATA_EXFILTRATION]: The skill does not access sensitive files or environment variables and contains no network-bound commands.
- [REMOTE_CODE_EXECUTION]: There are no scripts, package installations, or remote download patterns that could lead to unauthorized code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process implementation plans and designs, which constitutes an ingestion point for external data. However, the skill does not define any automated tools or write capabilities in the provided scripts, and the frontmatter explicitly disables model invocation, mitigating potential exploitation surfaces.
Audit Metadata