assemblyai
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly exposes actions that fetch and return transcripts and transcript components from AssemblyAI (e.g., "Create Transcript", "Get Transcript", "Get Paragraphs", "Get Sentences", "Search Words in Transcript"), which ingest arbitrary user-provided audio/URLs and return untrusted, user-generated text that the agent is expected to read and could materially influence subsequent decisions.
Audit Metadata