assemblyai-rate-limits
Warn
Audited by Snyk on May 19, 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). This skill's workflow (Step 2 "audioUrls" and the transcribeWithBackoff/queuedTranscribe calls in SKILL.md) clearly ingests arbitrary public audio URLs and transcribes them via AssemblyAI, so untrusted third-party audio content could influence transcripts and thus agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata