ir-playbook

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime LLM context is shaped by the provided incident data fields (e.g., “Incident trigger” and “IOCs/alert/user report” under SKILL.md:30-41), which commonly originate from outsider-authored sources such as SIEM/EDR alert text, external notifications, or attacker-controlled log/email content that is attacker-influenced free text; despite having an injection safety notice, this still indicates outsider-derived prose is ingested for analysis.