playwriter
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
playwriterCLI to perform browser actions as part of its core functionality. - [EXTERNAL_DOWNLOADS]: The skill fetches the
playwriterpackage from the public npm registry, which is a well-known service. - [REMOTE_CODE_EXECUTION]: The skill uses
npxto download and run the Playwriter tool and executes arbitrary JavaScript in the browser using the tool's execution flag. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
- Ingestion points: The skill reads page URLs, titles, accessibility snapshots, and console logs from active tabs (SKILL.md).
- Boundary markers: No delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The skill can execute JavaScript, click elements, and perform other browser interactions (SKILL.md).
- Sanitization: No evidence of sanitization or filtering of the content retrieved from the browser.
Audit Metadata