playwright
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @playwright/cli package from the npm registry. This is an official tool from Microsoft, which is a trusted organization.
- [COMMAND_EXECUTION]: A bash wrapper script (playwright_cli.sh) is used to execute browser automation commands locally on the system.
- [REMOTE_CODE_EXECUTION]: The skill provides eval and run-code commands that enable the execution of dynamic JavaScript within the browser context.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it extracts and processes data from external web pages.
- Ingestion points: The agent reads web content through browser snapshots (pwcli snapshot) and explicit data extraction (pwcli eval).
- Boundary markers: No explicit markers are implemented to distinguish web content from system instructions.
- Capability inventory: The skill can navigate the web, interact with forms, and execute JavaScript in the browser.
- Sanitization: Extracted data is not visibly sanitized or filtered before being processed by the agent.
Audit Metadata