maltego

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs running transforms such as "Domain – To Website", "Person – To Social Accounts", "Shodan Search", and WHOIS/DNS queries that fetch and ingest public websites and user-generated social content which the agent is expected to read and use to drive graph-building and follow-up transforms, creating a clear vector for indirect prompt injection.