skills/mizchi/skills/playwright-cli/Gen Agent Trust Hub

playwright-cli

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates interaction with external websites using Playwright, which establishes a potential ingestion point for untrusted data that could influence the agent.
  • Ingestion points: External URLs used with codegen, screenshot, and pdf commands in SKILL.md.
  • Boundary markers: Absent; the instructions do not provide explicit delimiters to separate external content from agent instructions.
  • Capability inventory: Use of npx playwright for shell-based browser automation in SKILL.md.
  • Sanitization: Absent; there are no specific steps to sanitize or filter content retrieved from URLs.
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to download necessary browser binaries from the official Playwright toolchain.
  • Evidence: Use of npx playwright install and npx playwright install chromium --with-deps in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:29 AM