bolna-extraction-designer
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust prompt engineering framework (the 7-part skeleton) designed to create predictable and secure extraction logic for transcripts.
- [SAFE]: All external tool references (create_disposition, bulk_create_dispositions, test_dispositions, list_dispositions) are standard MCP components for the Bolna platform and are used within their intended scope.
- [SAFE]: The skill provides explicit guidance on 'anti-patterns' and 'guardrails', which helps prevent common LLM misconfigurations and improves the reliability of the generated prompts.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized persistence mechanisms was found across the instructions or reference files.
Audit Metadata