aeon-deep-research

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses web search or fetches arbitrary web pages and documents based on the search topic, exposing the agent to low-trust outsider-authored text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The catalog setup instructs installation from an external GitHub repository URL, which constitutes an operational dependency.