debug-bolna-calls

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses raw execution logs and transcripts from Bolna's public API (e.g., GET /executions/{id} and GET /executions/{id}/log), which contain untrusted user-generated content, LLM reasoning_content, and tool payloads that the diagnostic workflow reads and uses to drive decisions—creating a clear avenue for indirect prompt injection.