webapp-testing
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for starting a local development environment using
docker compose. - [PROMPT_INJECTION]: The skill's use of browser automation creates a surface for indirect prompt injection, as the agent processes data from the application under test.
- Ingestion points: Web page content accessed via Playwright in the Python script within
SKILL.md. - Boundary markers: None present; no instructions are provided to the agent to treat page content as untrusted data.
- Capability inventory: The skill enables the agent to execute Python scripts with browser control capabilities via the Playwright library.
- Sanitization: Content from the web application is processed without explicit sanitization or filtering.
Audit Metadata