deepgram-python-management-api
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for creating and persisting Voice Agent configurations that include a prompt field in the think provider block. This is a potential surface for indirect prompt injection where malicious instructions could be stored and subsequently influence an agent's behavior. Evidence:
- Ingestion points: The
configparameter inclient.voice_agent.configurations.createandclient.voice_agent.configurations.update(SKILL.md). - Boundary markers: None present in the documented JSON examples.
- Capability inventory: Capability to write persistent configurations to the Deepgram Management API.
- Sanitization: No explicit sanitization or validation of the prompt content is shown in the examples.
Audit Metadata