yutori-computer-use

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to execute CLI commands using uvx (a Python package runner). These commands (yutori-mcp login, yutori-mcp computer-use setup, etc.) are specific to the vendor's platform and are used for initialization and task execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface by ingesting user-provided tasks ($ARGUMENTS) to drive desktop automation. While this is the primary purpose of the skill, it includes safety guidelines for the agent, such as limiting execution time and step counts, which help mitigate risks associated with processing untrusted automation requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 10:28 PM
Security Audit — agent-trust-hub — yutori-computer-use