skills/amit-t/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No security issues or malicious patterns were identified during the analysis of the skill's instructions and metadata.
  • [NO_CODE]: The skill is composed exclusively of Markdown instructions for the AI agent. It does not include any scripts, binaries, or configuration files that execute code.
  • [PROMPT_INJECTION]: The instructions do not contain any bypass markers, override commands, or attempts to extract system prompts. The 'grill' persona is a task-oriented role-play that remains within safety boundaries.
  • [DATA_EXFILTRATION]: No network-related commands (like curl or wget) or access to sensitive file paths (like .env or .ssh) are present in the skill.
  • [EXTERNAL_DOWNLOADS]: The documentation references a trusted installation source (vercel-labs/skills), which is a well-known service for managing AI agent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 01:48 AM
Security Audit — agent-trust-hub — grill-me