kol-creator-discovery

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

• Third-party content exposure detected (low risk: 0.10). The agent skill searches and fetches similar creator profiles and metadata from the AIsa WaveInflu API based on user-provided profile URLs or content directions, making outsider-authored bio/description texts a low-risk active fetch.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains an operational dependency on the AIsa API service hosted at aisa.one and api.aisa.one, which supplies behavior-selecting API integrations and execution logic.