uipath-test
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides the agent with the ability to ingest and summarize external data from test executions, which is a potential surface for indirect prompt injection.
- Ingestion points: The agent reads content from test logs (
uip tm testcaselog list), assertion messages (uip tm testcaselog list-assertions), step logs (uip tm teststeplog list), and Playwright test metadata (names and labels) stored on the platform. - Boundary markers: The instructions do not explicitly require the agent to use delimiters or ignore instructions found within the processed test data.
- Capability inventory: The skill possesses significant capabilities including command execution via the
uipCLI, file read/write access, and network interaction through the platform CLI. - Sanitization: There are no explicit sanitization or validation steps mentioned for data retrieved from test logs before it is processed into summaries or reports.
- [COMMAND_EXECUTION]: The skill relies heavily on executing shell commands via the
uipCLI andBashtool to perform CRUD operations on Test Manager resources, pack testing suites, and manage platform artifacts. These operations are consistent with the primary purpose of a UiPath management skill.
Audit Metadata