script-kit-ui-testing

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local build commands using cargo build and interact with a local binary ./target/debug/script-kit-gpui.
  • [COMMAND_EXECUTION]: Implements a JSON-based protocol to execute local scripts by passing absolute file paths to the application binary (e.g., {"type":"run","path":"..."}).
  • [DATA_EXFILTRATION]: Provides instructions to capture screenshots of the application window using an internal SDK function and save them to a local .test-screenshots/ directory for visual verification.
  • [DATA_EXFILTRATION]: Accesses local application logs located at ~/.scriptkit/logs/script-kit-gpui.jsonl to verify layout and execution behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 05:09 AM