all-agentic-architectures

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses Tavily search to fetch and process web content, exposing the agent to arbitrary outsider-authored free text from search results.

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

• Potentially malicious external URL detected (high risk: 0.70). The repository clone URL references an unofficial personal GitHub repository, making it a weak/unknown/suspicious operational dependency.