grill-me

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, such as hardcoded credentials or unauthorized data exfiltration, were found.
  • [PROMPT_INJECTION]: The skill uses codebase exploration to answer questions, which is an indirect prompt injection surface. 1. Ingestion points: Local codebase files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: File system read access (SKILL.md). 4. Sanitization: Not specified. This surface is part of the skill's primary functional design and is considered safe within the intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 01:04 PM