event-speaker-kit

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests arbitrary user-pasted text, uploaded files, and fetched event pages during Step 2 and Step 4.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching external event pages via URL (e.g., fourkites.ai, m2pfintech.com, tejasnetworks.com) during runtime, establishing an inbound operational dependency on arbitrary third-party web content with unknown or weak provenance.