webapp-testing
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is authored by Anthropic and its functionality is entirely consistent with its stated purpose of providing a testing toolkit for local web applications.
- [COMMAND_EXECUTION]: The skill provides templates for Python scripts using the Playwright library to automate browser interactions. This is standard and expected behavior for the defined use case.
- [DATA_EXFILTRATION]: The skill interacts with local services (localhost) and writes debug artifacts, such as screenshots and session state, to local temporary directories (/tmp/). No unauthorized network activity or external transmission of data was detected.
- [PROMPT_INJECTION]: The skill includes a 'Security Notice' section that explicitly advises on the necessity of input sanitization for dynamic selectors and test data to mitigate risks from untrusted content.
Audit Metadata