spectrum

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests inbound messages from external chat and messaging providers via app.messages, which exposes the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The terminal provider downloads a standalone binary from GitHub Releases during setup, constituting a weak remote operational dependency.