skills/epicenterhq/epicenter/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, external downloads, or obfuscated content were detected. The skill is entirely composed of natural language instructions.
  • [NO_CODE]: This skill contains no executable scripts or package dependencies; it functions as a behavioral prompt.
  • [PROMPT_INJECTION]: The instruction to explore the codebase to answer questions creates a surface for indirect prompt injection if the codebase contains untrusted or adversarial content.
  • Ingestion points: Local codebase files (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Read-access to project files (SKILL.md).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 08:12 PM