agent-email-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to record data.password from CLI JSON and to pass passwords on the command line (e.g., --password <password>), which requires the agent to handle and emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly reads and processes email messages from disposable inboxes (see SKILL.md Workflow steps 3–4 and Operational Guidance, which instruct using agent-email read/show to retrieve full message bodies and "verification links, codes, or full content extraction"), meaning it ingests untrusted, third‑party user-generated content that can influence agent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes the external CLI "agent-email" and explicitly instructs installing it from npm (https://www.npmjs.com/package/@zaddy6/agentemail), so remote code fetched from that package would be installed and executed at runtime and is a required dependency.