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

uipath-servo

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install or run the @uipath/servo package from the official npm registry. This is a trusted resource provided by the vendor.
  • [PROMPT_INJECTION]: The skill provides tools to read data from external user interfaces, which constitutes a surface for indirect prompt injection. This is an inherent risk of UI automation functionality.
  • Ingestion points: Element attributes, text, and table data retrieved via servo snapshot, servo get, and servo extract-table (described in SKILL.md).
  • Boundary markers: No specific markers or delimiters are mandated in the instructions for the agent to use when processing UI output.
  • Capability inventory: The skill has the ability to interact with the system via shell commands and UI-specific actions like clicking and typing.
  • Sanitization: Data is retrieved directly from the application's accessibility tree without explicit sanitization steps defined in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 04:10 PM