Skills
skills/software-mansion/argent/argent-simulator-interact/Gen Agent Trust Hub

argent-simulator-interact

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides tools like gesture-tap, keyboard, and button to execute actions within an iOS simulator environment.
  • [DATA_EXFILTRATION]: The open-url tool facilitates opening arbitrary URLs, which constitutes a network operation from the simulator.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through the ingestion of untrusted data from the simulator screen.
  • Ingestion points: describe, screenshot, and debugger-component-tree tools in SKILL.md.
  • Boundary markers: No delimiters or warnings are specified for processing screen data.
  • Capability inventory: The skill can perform taps, keyboard input, and open URLs based on interpreted screen data.
  • Sanitization: No sanitization or validation of the ingested UI content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 06:19 AM