grill-me

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill directs the agent to explore the codebase to answer questions, which allows untrusted data from the codebase to be processed as instructions.\n
  • Ingestion points: Local codebase files (referenced in SKILL.md).\n
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present.\n
  • Capability inventory: The agent performs file reading and codebase analysis.\n
  • Sanitization: No sanitization or validation of the codebase content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 10:43 AM