testdino-audit
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- Audit Data Ingestion Surface: The skill is designed to process external Playwright test code and context retrieved from the TestDino MCP server. As with any process that interprets untrusted content, this represents a potential surface for indirect prompt injection where embedded instructions could attempt to influence the agent. The skill uses Model Context Protocol (MCP) tools for this interaction, providing a managed boundary for data exchange.
- Local Report Generation: The workflow instructs the agent to write audit findings to a local markdown file, such as TEST-AUDIT.md. This is a standard functional capability for a development tool, allowing users to maintain a local record of findings within their project environment.
- External Resource Interaction: The skill communicates with external auditing services through specific MCP tools like get_audit_report and submit_audit_report. This ensures that network operations and data submissions are scoped to the intended functionality of the TestDino audit service.
Audit Metadata