skills/efesto-cloud/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of plain-text instructions that define an interaction model for reviewing plans. It does not include any executable code, scripts, or external network requests.
  • [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection as it processes untrusted user designs and codebase content. 1. Ingestion points: User-provided plans and local codebase files. 2. Boundary markers: Absent. 3. Capability inventory: Codebase exploration through file-reading tools. 4. Sanitization: Absent. The instructions are behavioral and do not attempt to bypass safety constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 07:42 PM
Security Audit — agent-trust-hub — grill-me