grillme
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of instructional text providing a framework for an AI agent to guide a user through research topic selection.
- [NO_CODE]: There are no scripts, binaries, or configuration files provided that would result in code execution on the user's environment.
- [PROMPT_INJECTION]: The instructions are pedagogical in nature and do not contain patterns typical of prompt injection attacks, such as attempts to bypass safety filters or ignore prior instructions.
- [DATA_EXFILTRATION]: There are no network-capable commands (e.g., curl, wget) or hardcoded endpoints that could be used to exfiltrate user data.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in the skill's metadata or body.
Audit Metadata