xquik-data

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow is about using Xquik to collect/monitor/extract X/Twitter data via REST/OpenAPI/MCP/webhooks, and it does not describe ingesting outsider-authored free text directly into the model without first choosing specific user-supplied items/endpoints from Xquik-managed data flows.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to fetch live specifications/docs (e.g., https://xquik.com/openapi.json and https://docs.xquik.com/api-reference/overview) at runtime to determine endpoint names and request/response shapes, meaning remote content would directly control the agent's prompt/behavior.