skills/evans-sam/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, external downloads, or exfiltration attempts were detected.
  • [NO_CODE]: The skill consists exclusively of instructions without any embedded executable scripts or commands.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it instructs the agent to read and process content from the local codebase.
  • Ingestion points: Local codebase files (SKILL.md).
  • Boundary markers: None specified to protect against instructions embedded in code or configuration files.
  • Capability inventory: The skill relies on the agent's file-reading tools to resolve decision dependencies.
  • Sanitization: No sanitization or validation of codebase content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 06:03 PM