skills/uipath/skills/uipath-planner/Gen Agent Trust Hub

uipath-planner

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines clear operational boundaries by prohibiting the agent from writing automation code (XAML, C#, Python) or performing any actions outside of planning and non-mutating discovery.
  • [SAFE]: Filesystem interactions are limited to a hardcoded Bash command for environment probing and reading standard project metadata files like project.json. These operations do not target sensitive system files or user credentials.
  • [SAFE]: No remote code downloads, network exfiltration, or obfuscation techniques were identified within the skill instructions.
  • [SAFE]: The skill processes user-provided documents (PDD/SDD) to inform its planning logic. While this represents a surface for indirect prompt injection, the risk is minimized by the skill's lack of executable capabilities and its focus on generating descriptive markdown plans.
  • [SAFE]: The skill enforces human-in-the-loop validation for non-trivial tasks via its Plan Mode tools, ensuring the user reviews the generated plan before any further action is taken by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 10:47 AM
Security Audit — agent-trust-hub — uipath-planner