agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains examples that embed credentials/passwords directly in commands (e.g., agent-browser fill @e2 "password123" and fill @e2 "$PASSWORD"), which instructs the agent to include secret values verbatim in generated output and is high-risk for exfiltration.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to open and scrape arbitrary public URLs (e.g., "agent-browser open " in SKILL.md and capture-workflow.sh's TARGET_URL + agent-browser snapshot/get text), so untrusted third‑party page content is fetched and interpreted as part of the workflow and could influence subsequent actions.