analyzing-campaign-attribution-evidence

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

• Third-party content exposure detected (high risk: 0.80). The skill clearly fetches and ingests public threat-intel data that can influence attribution (e.g., scripts/process.py's compare_ttps path uses the attackcti client to pull MITRE ATT&CK groups/techniques, SKILL.md lists MISP/OpenCTI as required sources, and references/api-reference.md shows curl examples for PassiveTotal/VirusTotal), so untrusted third‑party content is read and used to drive analysis and decisions.