disposable-email-address

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

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors and ingests external email messages via the check action, which allows reading outsider-authored email bodies directly into the agent.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill describes remote API calls to AgentPMT and instructs installing dependencies via npx skills add AgentPMT/agent-skills, which is a common/reputable unofficial publisher source (medium tier).