evo-executing-plans
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill defines a procedural workflow for plan execution and human checkpoints. It does not involve any dangerous operations, file system modifications outside of plan-directed tasks, or credential handling.
- [NO_CODE]: The skill is comprised entirely of Markdown instructions and does not include scripts, binaries, or external software dependencies.
- [PROMPT_INJECTION]: The skill reads and follows instructions from an external 'plan file', which is an ingestion point for potential indirect prompt injection. However, the risk is mitigated by specific instructions to 'Review critically' before starting, 'Raise concerns with your human partner', and 'Stop executing immediately' if instructions are unclear or verifications fail. The human-in-the-loop requirement for batch approvals provides a strong security boundary.
Audit Metadata