playwright-bowser

Warn

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill utilizes the Bash tool to run the playwright-cli utility, which is the intended primary purpose of this automation skill.
  • [REMOTE_CODE_EXECUTION] (MEDIUM): The playwright-cli documentation within the skill identifies a run-code <code> command. This feature enables the execution of arbitrary JavaScript within the browser context, representing a dynamic execution risk if the input code is not strictly controlled or is derived from untrusted sources.
  • [PROMPT_INJECTION] (LOW): This skill is highly susceptible to indirect prompt injection (Category 8) due to its nature as a web browsing tool.
  • Ingestion points: External data is ingested via commands like open, goto, and snapshot in SKILL.md.
  • Boundary markers: None. The skill does not provide instructions to the agent on how to separate user/system instructions from content retrieved from the web.
  • Capability inventory: The skill can perform network operations, write files (screenshots/PDFs), and execute scripts via run-code as defined in SKILL.md.
  • Sanitization: There are no mentioned mechanisms for sanitizing or filtering the content parsed from web pages.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 22, 2026, 10:07 PM