hunting-for-command-and-control-beaconing

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 5 "Analyze Domain/IP Reputation") and the API reference include explicit queries to public threat‑intelligence/WHOIS/certificate‑transparency sources (e.g., Abuse.ch ThreatFox and OTX) that the agent is expected to consult and act on, exposing it to untrusted, user‑provided third‑party content that can influence follow-up actions.