playwright-automation

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The install.py script uses subprocess.run to execute hardcoded shell commands for environment setup, specifically installing the Playwright package and the Chromium browser engine.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the playwright library and Chromium binaries from standard package registries (PyPI) and official browser distribution channels.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from the web, creating a surface for indirect prompt injection. * Ingestion points: Web content is retrieved through methods like page.goto, page.content, and page.text_content in SKILL.md and the example scripts examples/basic.py and examples/search_example.py. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided snippets. * Capability inventory: The skill is configured with Bash, Exec, Read, and Write capabilities in SKILL.md metadata, allowing the agent to perform system-level actions based on scraped content. * Sanitization: There is no evidence of data sanitization or filtering applied to the scraped web content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 01:18 AM