playwright-cli

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Bash to run Playwright CLI commands like test, codegen, and open. These are standard operations for web automation and do not exhibit malicious intent.
  • [EXTERNAL_DOWNLOADS]: Browser binaries and OS dependencies are downloaded from official Microsoft infrastructure through the playwright install command. These sources are trusted.
  • [DATA_EXFILTRATION]: The skill supports the persistence of browser authentication states using storage files. While a standard feature, users should treat these files as containing sensitive credentials.
  • [PROMPT_INJECTION]: The skill's ingestion of arbitrary URLs creates a surface for indirect prompt injection. Evidence: 1. Ingestion points: URL parameters in commands. 2. Boundary markers: None. 3. Capability inventory: Bash command execution. 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:33 AM