skills/gracefullight/krds/plan/Gen Agent Trust Hub

plan

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill file contains only descriptive metadata and a single instruction to read a local file. No executable code, network requests, or obfuscated content were detected.
  • [PROMPT_INJECTION]: The instruction to follow external files like .agents/workflows/plan.md is a standard pattern for organizing workflows but introduces a surface for indirect prompt injection if the contents of that local file are compromised.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 07:00 PM
Security Audit — agent-trust-hub — plan