defense-threat-intel

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow collects public X/Twitter posts via the Xquik API/MCP, directly ingesting outsider-authored social media content into the agent's runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to interact with Xquik via https://xquik.com/mcp and https://xquik.com/api/v1, which are arbitrary third-party services with unknown provenance, constituting a high-tier unverifiable operational dependency.