grill-me

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a structured conversational workflow and do not contain any obfuscation, malicious commands, or credential harvesting patterns.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing user-supplied plans and project files.
  • Ingestion points: User-provided designs/plans and local codebase files (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: File reading/exploration of the local project directory (SKILL.md).
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:08 AM
Security Audit — agent-trust-hub — grill-me