skills/dotoricode/orca/computer-use/Gen Agent Trust Hub

computer-use

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes UI accessibility trees from arbitrary desktop applications, creating a surface for indirect prompt injection. * Ingestion points: The ORCA computer get-app-state command returns the treeText of targeted applications (SKILL.md). * Boundary markers: No specific delimiters or safety wrappers are defined for the ingested UI content. * Capability inventory: The skill possesses extensive system interaction capabilities, including click, set-value, type-text, and hotkey (SKILL.md). * Sanitization: There is no evidence of sanitization or filtering applied to the UI data before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill operates by executing local CLI commands (orca, orca-dev, etc.) with various flags and arguments to control the desktop environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:36 AM
Security Audit — agent-trust-hub — computer-use