browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed secrets directly in CLI commands (plain-text passwords in fill commands and a --headers '{"Authorization":"Bearer "}' example), which would require the agent to insert secret values verbatim into its output.

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to open and interact with arbitrary external URLs (e.g., "Core Workflow" and commands like agent-browser open <url> and agent-browser snapshot -i in SKILL.md), causing it to fetch and parse untrusted public web content whose instructions or content can alter subsequent actions.