grill-me

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to facilitate a structured interview process using the AskUserQuestion tool. It does not contain any malicious patterns such as prompt injection, persistence mechanisms, or obfuscation.
  • [COMMAND_EXECUTION]: The instructions permit the agent to explore the codebase or files to answer questions independently. This is a standard feature for developer-oriented AI agents and does not involve the execution of untrusted scripts or the acquisition of elevated privileges.
  • [DATA_EXFILTRATION]: There are no network-capable commands (such as curl or wget) or hardcoded credentials. The skill operates entirely within the local environment and does not attempt to send data to external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 03:16 AM
Security Audit — agent-trust-hub — grill-me