grill-me
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected. The skill is composed entirely of instructional text.
- [PROMPT_INJECTION]: The instructions do not attempt to bypass safety guidelines, extract system prompts, or override agent constraints.
- [DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or attempts to access sensitive environment variables or private keys.
- [COMMAND_EXECUTION]: The skill does not invoke shell commands or subprocesses. The instruction to 'explore the codebase' utilizes standard read-only tool capabilities within the agent's environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided plans and designs (untrusted data). While this is an ingestion surface, the lack of dangerous write capabilities or network operations minimizes the risk to a negligible level.
Audit Metadata