playwright-cli

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes content from external websites (HTML, console logs, and accessibility trees) that may contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Web content is ingested via playwright-cli snapshot, playwright-cli console, playwright-cli network, and playwright-cli eval as documented in core-commands.md, tracing-and-debugging.md, and running-custom-code.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation to prevent the agent from obeying instructions found on web pages.
  • Capability inventory: The agent has the capability to execute custom JavaScript (run-code), write files (screenshot, pdf, state-save), and access local system resources like the clipboard and storage.
  • Sanitization: No evidence of input validation, escaping, or sanitization of ingested web data before processing is present in the skill instructions.
  • [COMMAND_EXECUTION]: The skill provides an interface to a local command-line tool, playwright-cli, which allows the agent to perform complex browser operations. This includes the run-code subcommand which executes arbitrary JavaScript within the browser context, as seen throughout advanced-workflows.md and running-custom-code.md.
  • [DATA_EXFILTRATION]: The skill includes multiple commands that provide access to sensitive session data, including cookies, localStorage, and clipboard content. While these are necessary for the skill's purpose, they represent a surface for data exposure or exfiltration if the agent is directed to process them maliciously.
  • Evidence: Commands such as cookie-list, localstorage-get, and state-save (in storage-and-auth.md) enable reading and writing browser state to the local filesystem.
  • [EXTERNAL_DOWNLOADS]: The skill instructions (in core-commands.md) direct users to install browsers and additional components using playwright-cli install --skills and playwright-cli install-browser.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 08:14 AM
Security Audit — agent-trust-hub — playwright-cli