NYC
skills/smithery/ai/executing-plans/Gen Agent Trust Hub

executing-plans

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Workflow Analysis] (SAFE): The skill serves as a procedural guide for batch task execution. It contains no executable logic or scripts, relying instead on the agent's internal reasoning and other specialized skills.
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and act upon implementation plans. While these plans constitute untrusted data, the skill mitigates risk by requiring a 'Critical Review' step and human feedback loops before proceeding with implementation.
  • Ingestion points: Implementation plan file (Step 1).
  • Boundary markers: Not explicitly defined in the input format, but the process mandates a critical review phase.
  • Capability inventory: No direct capabilities; coordinates external workflow skills.
  • Sanitization: Relies on human-in-the-loop validation and critical review by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:35 PM