malware-analysis

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly queries external threat‑intelligence feeds (e.g., "Query VirusTotal or similar via API" in Key Capabilities/Integration) and ingests those third‑party, user‑submitted results which are used to cross‑reference IOCs and drive follow‑up actions (e.g., blocking IPs), so it exposes the agent to untrusted third‑party content that could influence behavior.