demo-video
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute local JavaScript and Bash scripts to record interactions and encode frames into video files.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it navigates to and interacts with web applications which may contain untrusted content.
- Ingestion points: External or local web pages accessed via Playwright.
- Boundary markers: None identified in the provided instructions.
- Capability inventory: Execution of Node.js and Bash scripts, and browser control.
- Sanitization: No explicit validation or sanitization of web content is described.
Audit Metadata