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

uipath-feedback

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute the uip CLI for diagnostic data gathering and feedback submission. Commands include uip --version, uip login status, and uip feedback send.- [DATA_EXFILTRATION]: The skill is designed to collect and transmit data to UiPath for troubleshooting. This includes truncated project files (e.g., .flow, project.json, bindings.json), environment metadata, and summarized user prompts. Security is maintained through mandatory user confirmation and a preview step prior to transmission.- [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from project files and user conversations. It mitigates injection risks by using a structured sanitization protocol to redact sensitive values (tokens, secrets, GUIDs) and providing a human-in-the-loop validation step where the user must approve the report content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:06 PM
Security Audit — agent-trust-hub — uipath-feedback