uipath-ixp
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates exclusively through the uip CLI, which is a vendor-specific tool for the skill's author (uipath). It does not attempt to execute arbitrary shell commands or remote scripts.
- [SAFE]: File system access is restricted to a dedicated temporary workspace (/tmp/ixp/), and the skill does not attempt to read sensitive credentials or system configuration files.
- [SAFE]: The skill implements a secure pattern for data handling by writing JSON payloads to temporary files rather than passing complex strings directly to the shell, which prevents command injection and data corruption.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes external document files and taxonomy configurations. This is an inherent risk of document extraction tasks and is mitigated by instructions that require the agent to validate extractions against specific data types rather than literal page content.
Audit Metadata