post-acceptance

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

• Third-party content exposure detected (low risk: 0.10). The workflow optionally integrates Xquik MCP (references/xquik-promotion.md) to search and read public X (Twitter) posts, profiles, and display names, exposing the agent to outsider-authored free text via an active search/fetch retrieval model.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs connection to a hosted remote service at https://xquik.com/mcp for setup and runtime behavior, providing an operational dependency with unknown/third-party provenance.