malware-scan-yara

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly references and requires using community YARA rules from the public GitHub repo https://github.com/Yara-Rules/rules, meaning it ingests untrusted, user-contributed third-party rule content that the agent must read/interpret as part of scanning.