grill-me

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is entirely behavioral, providing instructions to the AI agent on how to conduct a one-at-a-time interview to resolve project requirements.
  • [NO_CODE]: The skill does not include any scripts, shell commands, or external dependencies. All logic is contained within natural language instructions and structural patterns.
  • [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The context-checking patterns (e.g., reading package.json) are limited to benign project configuration files for legitimate context gathering.
  • [PROMPT_INJECTION]: There are no attempts to override system safety guidelines or bypass agent constraints. The instructions focus on reducing ambiguity and cognitive load for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 11:58 PM
Security Audit — agent-trust-hub — grill-me