ez-ui
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Playwright library to automate browser interactions, including logging into Home Assistant and capturing screenshots of dashboards. It also provides usage examples using
node -eto run short scripts for browser control.\n- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to access and read data from Home Assistant dashboards. If these dashboards contain content (such as entity names or sensor values) crafted as instructions, it could influence the agent's behavior.\n - Ingestion points: Web UI content fetched via Playwright and processed through screenshots or DOM interaction (SKILL.md, scripts/browser-login.mjs).\n
- Boundary markers: Not explicitly defined in the prompt templates to separate dashboard data from agent instructions.\n
- Capability inventory: Browser interaction, network access to the local Home Assistant service, and local session state management.\n
- Sanitization: None detected for the ingested UI content before processing.
Audit Metadata