playwright-cli
Warn
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The
playwright-cli run-codeandplaywright-cli evalcommands allow for the execution of arbitrary JavaScript code within the browser context and the tool's execution environment. This provides a direct mechanism for the agent to execute unverified logic beyond the pre-defined CLI commands. - [DATA_EXFILTRATION]: The skill can access sensitive browser data, including cookies, localStorage, and session storage via commands like
cookie-getandlocalstorage-get. It also includes patterns for reading the system clipboard usingnavigator.clipboard.readText()withinrun-codeblocks. - [DATA_EXFILTRATION]: The tool facilitates writing sensitive data to the local file system. Specifically, the
state-savecommand exports all session cookies and local storage items to a JSON file, and other commands allow saving screenshots, PDFs, and video recordings to local paths. - [COMMAND_EXECUTION]: The skill makes extensive use of the
playwright-clitool to interact with the system and browser. This includes process management and file system operations that are necessary for browser automation but expand the agent's capability to modify the local environment. - [PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection when navigating to untrusted websites, as it ingests and processes third-party page content.
- Ingestion points: External URLs and page content are ingested via
open,goto,snapshot, andevalcommands as documented inSKILL.mdandcore-commands.md. - Boundary markers: The documentation includes a "Security" section in
SKILL.mdthat warns users to only target authorized applications and treat extracted text as untrusted data. - Capability inventory: The skill possesses capabilities for arbitrary JavaScript execution (
run-code), file system writes (state-save,screenshot), and access to sensitive browser storage. - Sanitization: The documentation suggests manual sanitization of extracted content but does not provide automated validation mechanisms within the tool itself.
Audit Metadata