cursor-control-ui
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external UI surfaces (web pages, Electron apps, or IDE components), which could potentially contain malicious instructions.
- Ingestion points: UI snapshots, screenshots, console logs, and network logs captured via Playwright or CDP (described in
SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the captured UI data.
- Capability inventory: The skill possesses the ability to write to the local file system (screenshots, heap snapshots) and perform browser actions like navigation, clicking, and typing.
- Sanitization: No specific sanitization or filtering of the content retrieved from the UI is described.
- [DYNAMIC_EXECUTION]: The skill provides templates and instructions for the agent to dynamically generate and execute local browser automation scripts using Playwright and the Chrome DevTools Protocol (CDP). This script generation is the core intended functionality for local UI verification.
Audit Metadata