browsing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes explicit examples that type plaintext passwords into form payloads (e.g., {action:"type", payload:"pass123"}) and auto-captures page content/screenshots, which requires the agent to handle and emit secret values verbatim and risks exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). The skill intentionally navigates to arbitrary public URLs and ingests page content — SKILL.md and EXAMPLES.md (and the chrome-ws CLI docs) show actions like navigate/extract/eval and cross-site workflows, and lib/capture.js (generateMarkdown / capturePageArtifacts) executes page scripts and saves/exposes untrusted webpage content that the agent then uses to drive follow-up actions (e.g., filling forms, typing extracted data), so third‑party pages can implicitly inject instructions.