assemblyai
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the official
assemblyaiSDKs for Python and JavaScript/TypeScript. It also includes integrations for well-known voice agent frameworks such aslivekit-agentsandpipecat-ai. - [COMMAND_EXECUTION]: Documentation provides standard
curlexamples for interacting with the AssemblyAI REST API endpoints, which is expected for an API-focused skill. - [CREDENTIALS_UNSAFE]: The skill correctly uses placeholders like
YOUR_API_KEYin examples and explicitly advises users to manage secrets using environment variables (e.g.,process.env.ASSEMBLYAI_API_KEY). - [PROMPT_INJECTION]: The skill addresses the attack surface of indirect prompt injection when processing untrusted audio data. It mitigates this risk by providing examples that use XML-style boundary markers (e.g.,
<transcript>) to isolate untrusted content from system instructions.
Audit Metadata