grill-me

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were detected. The skill consists of high-level behavioral instructions for the AI agent.
  • [PROMPT_INJECTION]: The skill exhibits a standard surface for indirect prompt injection because it is designed to ingest and analyze user-provided content (plans or designs). While this is inherent to its primary purpose, no specific vulnerabilities were identified.
  • Ingestion points: User-provided plans or design documents processed during the 'interview' phase.
  • Boundary markers: None present in the instructions.
  • Capability inventory: Limited to codebase exploration and conversational interaction.
  • Sanitization: None implemented within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:57 PM
Security Audit — agent-trust-hub — grill-me