voice-agents

Warn

Audited by Snyk on Mar 13, 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 ingests untrusted user-generated speech from external transports/rooms (e.g., LiveKit rooms and Daily.co/WebSocket transports shown in SKILL.md and references/*.md) via STT and forwards those transcripts to the LLM in on_message/pipeline flows, so third-party content can directly influence agent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 03:05 PM
Issues
1