comet-browser-testing
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No evidence of prompt injection or safety bypass attempts was found. The skill uses prompt templates for browser testing, which are instructions for the testing tool rather than attempts to subvert the agent context.
- [DATA_EXFILTRATION]: No evidence of unauthorized data exfiltration. The skill performs local health checks and log parsing consistent with its testing purpose.
- [REMOTE_CODE_EXECUTION]: No evidence of remote code execution from untrusted URLs. The skill utilizes platform-integrated MCP tools and includes a fallback for local browser automation scripts via a code execution tool.
- [COMMAND_EXECUTION]: The skill includes shell scripts for health checks and workflow automation. These scripts perform standard operations such as log parsing and connectivity checks on project-local resources.
Audit Metadata