agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and workflow require embedding literal secrets into CLI commands (e.g., agent-browser fill @e4 "password123"), meaning an agent would need to include user credentials verbatim in its output/commands, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly automates and scrapes arbitrary external websites (e.g., "agent-browser open " and "agent-browser snapshot -i" / "agent-browser get text body") as shown in SKILL.md and references/commands.md, so the agent ingests untrusted third‑party web content that can drive actions.