momentic-test
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external sources, including test definition files and live content from web applications, which could potentially contain malicious instructions intended to manipulate agent behavior.\n
- Ingestion points: User-provided YAML test files, reusable module files, and DOM content or screenshots from target websites.\n
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested data.\n
- Capability inventory: The skill possesses file writing capabilities, browser automation control (forked Playwright/CDP), and subprocess execution via npx.\n
- Sanitization: No explicit sanitization or validation mechanisms are described for external content.\n- [DYNAMIC_EXECUTION]: The skill enables the agent to author and execute JavaScript in both Node.js and Browser environments to handle complex test logic and DOM interactions. While functional for E2E testing, this allows for the execution of dynamically created scripts.\n- [COMMAND_EXECUTION]: The instructions direct the agent to invoke the
momenticCLI tool vianpxfor linting and test execution tasks.
Audit Metadata