uloop-get-logs
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
uloopcommand-line tool to interface with the Unity engine and retrieve log data. - [PROMPT_INJECTION]: The skill ingests external data from Unity Console logs, which represents an indirect prompt injection surface as logs may contain messages influenced by untrusted inputs.
- Ingestion points: Unity Console log entries are read via the
uloop get-logscommand. - Boundary markers: No explicit delimiters or system instructions are used to distinguish the log content from the agent's own operational instructions.
- Capability inventory: This skill is restricted to reading and searching log data and does not perform additional sensitive operations.
- Sanitization: Log data is returned to the agent without escaping or sanitization of potential embedded instructions.
Audit Metadata