chrome-devtools

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly returns network request/response headers and inspects HTTP traffic (which can contain Authorization headers, cookies, or API keys), so using it can require the LLM to surface secret values verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to and loads arbitrary URLs (e.g., mcp__plugin_chromedev-tools_cdt__navigate_page and the /chromedev:inspect command in SKILL.md and examples), then captures DOM snapshots, console messages, network requests, and even runs page-evaluated JavaScript—meaning it ingests untrusted, public third-party page content and uses that content as input that can influence subsequent tool actions.