manage-violations

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly polls Bolna's API (e.g., GET /violations/list in scripts/list_violations.py) and its workflow (Operational workflow step 3 in SKILL.md) instructs the agent to pull related executions and raw call transcripts via GET /executions/{execution_id}, meaning the agent ingests third-party/user-generated call logs and descriptions which are used to triage and drive follow-up actions.