playwright

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @playwright/cli package. This package is the official command-line interface for the Playwright browser automation library and is used as intended.
  • [COMMAND_EXECUTION]: The skill uses a bash wrapper script (scripts/playwright_cli.sh) to execute browser automation commands like navigation, clicking, and data extraction.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its core function of processing external web content.
  • Ingestion points: The skill ingests external data via browser snapshots and navigation as described in SKILL.md.
  • Boundary markers: No explicit delimiters or boundary instructions are present to mitigate instructions embedded in processed web pages.
  • Capability inventory: The skill has network access and the ability to interact with browsers.
  • Sanitization: The skill definitions do not include logic for filtering or sanitizing content from the browser.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:59 PM
Security Audit — agent-trust-hub — playwright