skills/breezewish/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, hardcoded credentials, or unauthorized network operations were detected. The skill is purely instructional.
  • [NO_CODE]: The skill consists only of a SKILL.md file and does not include any accompanying scripts, executables, or code dependencies.
  • [PROMPT_INJECTION]: The skill instructs the agent to read current project files, documentation, and git history to understand the design context. This represents an indirect prompt injection surface where the agent could potentially ingest malicious instructions from within the project files.
  • Ingestion points: Local project files, documentation, and git history (SKILL.md)
  • Boundary markers: None present
  • Capability inventory: Agent relies on default tools for file system and git access
  • Sanitization: None present
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 06:06 AM
Security Audit — agent-trust-hub — grill-me