skills/baarai/artex/playwright-cli/Gen Agent Trust Hub

playwright-cli

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to navigate to external websites and ingest their content, which could contain malicious instructions. If the agent follows these instructions, it could abuse its capabilities to compromise user data. 1. Ingestion points: playwright-cli snapshot, playwright-cli find (SKILL.md), and playwright-cli eval (references/element-attributes.md). 2. Boundary markers: None identified. 3. Capability inventory: playwright-cli cookie-get, playwright-cli state-save, playwright-cli run-code, Bash(npx:*), Bash(npm:*), and file writing via download.saveAs. 4. Sanitization: None identified.
  • [DYNAMIC_EXECUTION]: The run-code and eval commands allow the agent to execute arbitrary JavaScript within the browser context. This is a core feature of the skill but presents a risk if the code logic is influenced by untrusted external data.
  • [COMMAND_EXECUTION]: The skill uses Bash to run CLI tools and package managers (npm, npx), which gives the agent significant control over the local execution environment.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the Playwright CLI and related testing tools from the official npm registry, which is a trusted and well-known source.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 11:17 PM