uloop-run-tests

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the 'uloop' CLI tool to run Unity tests (EditMode/PlayMode). This is the primary intended function of the skill and aligns with the provided description.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to read and diagnose failures from external NUnit XML files generated during test execution.
  • Ingestion points: XML result files located at '{project_root}/.uloop/outputs/TestResults/.xml'.
  • Boundary markers: Absent. There are no specified delimiters or instructions for the agent to ignore potentially malicious content within the test result files.
  • Capability inventory: The skill can execute shell commands via the 'uloop' tool.
  • Sanitization: Absent. The skill does not describe any validation or escaping of the XML content before the agent processes it for diagnosis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 02:16 AM
Security Audit — agent-trust-hub — uloop-run-tests