voice-transcribe
Warn
Audited by Snyk on Mar 1, 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.md explicitly instructs running the skill on user-provided voice memos (e.g., "when receiving voice memos (especially via whatsapp)"), so the agent ingests untrusted user-generated audio and then acts on the transcribed content, allowing third-party content to influence behavior.
Audit Metadata