Playwright Browser Automation

Warn

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
  • [DYNAMIC_EXECUTION]: The run.js script implements a custom execution wrapper that accepts arbitrary strings from command-line arguments, files, or standard input. It writes these strings to a temporary JavaScript file in the skill directory and executes them using the Node.js require() function. This enables the execution of dynamically generated automation logic at runtime via computed paths.
  • Evidence: run.js lines 180-184: fs.writeFileSync(tempFile, code, 'utf8'); require(tempFile);
  • [REMOTE_CODE_EXECUTION]: The skill automates the installation of dependencies and browser binaries from the official npm registry and the Playwright project's distribution servers.
  • Evidence: run.js lines 42-43: execSync('npm install', ...); execSync('npx playwright install chromium', ...);
  • Evidence: package.json scripts: setup and install-all-browsers.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from arbitrary external websites provided via user input or auto-detection. This creates an attack surface where malicious content on a webpage could attempt to influence the agent's behavior during the automation process.
  • Ingestion points: page.goto(TARGET_URL) in generated scripts and examples in SKILL.md, as well as link extraction and table data extraction helpers.
  • Boundary markers: The skill does not implement explicit delimiters or instructions to ignore embedded commands within the web content being processed.
  • Capability inventory: The skill has the ability to write files to /tmp, execute shell commands via the run.js wrapper, and perform network requests via the Playwright browser.
  • Sanitization: There is no evidence of sanitization or filtering of content scraped from external pages before it is processed by the agent.
  • [METADATA_POISONING]: The skill contains inconsistent author information across its metadata files, which could be misleading regarding its origin.
  • Evidence: SKILL.md frontmatter lists author: Claude Assistant.
  • Evidence: package.json lists "author": "lackeyjb".
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 29, 2026, 08:16 PM
Security Audit — agent-trust-hub — Playwright Browser Automation