phone-call
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill fetches and ingests untrusted, user-generated call transcripts and recordings from the fluents.ai API (see scripts/analyze_call.py and scripts/get_call_result.py which call FLUENTS_API_URL/v1/calls to retrieve and analyze the "transcript" and scripts/get_recording.py which downloads recordings), so third-party content is read and interpreted as part of the workflow.
Audit Metadata