ce-test-browser
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with Git, manage development servers, and control browser automation tools. Evidence includes the use of gh pr view, git diff, npm run dev, bin/dev, and agent-browser commands across SKILL.md and reference files.
- [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection as it instructs the agent to navigate to and inspect the rendered state of local web pages defined by the code being tested. 1. Ingestion points: Browser viewport content and console logs (references/route-and-report.md). 2. Boundary markers: None; the agent inspects the page state directly. 3. Capability inventory: Shell command execution, file system access (reading .env and package.json), and browser automation interaction. 4. Sanitization: Not present; the agent relies on its functional instructions.
Audit Metadata