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

uipath-agents

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing development tools like the uv package manager (via curl | sh from astral.sh) and the UiPath CLI (via npm install). These are well-known, legitimate services and tools relevant to the skill's purpose.
  • [COMMAND_EXECUTION]: Extensive use of the uip and uv CLI commands is documented for tasks such as agent scaffolding, environment management, and solution deployment. These commands are executed within the user's development context as part of the intended workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of agents that ingest external data, such as chat history, uploaded PDFs (via the DeepRAG capability), and CSV files (via BatchTransform). This represents an indirect prompt injection surface; however, the skill provides extensive documentation and workflows for mitigating these risks using built-in guardrails (PII detection, harmful content filtering, and prompt injection validators) and structured output contracts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:03 PM
Security Audit — agent-trust-hub — uipath-agents