skills/sones3/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, data exfiltration, or obfuscation techniques were identified in the skill instructions.- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to explore the codebase to answer questions. This creates a surface where the agent processes untrusted data from project files (comments, documentation, etc.), which could theoretically contain instructions intended to influence the agent's reasoning during the interview. This is a common feature of coding assistants.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 08:25 PM