analyzing-campaign-attribution-evidence

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public third‑party threat intelligence (e.g., attackcti/attack_client used in SKILL.md Step 3 and scripts/process.py, prerequisites listing MISP/OpenCTI, and API examples for PassiveTotal/VirusTotal/WHOIS in references/api-reference.md), and that external data is parsed and used to drive attribution scoring and decisions—creating a clear path for untrusted, user-contributed content to influence agent behavior.