telnyx-ai-inference-java
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official Telnyx Java SDK (
com.telnyx.sdk:telnyx:6.84.0) for Maven and Gradle. These are legitimate vendor-owned resources provided by the author to enable the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill includes functions that process untrusted external data, such as chat messages, audio transcriptions, and file summaries. This creates a standard surface for indirect prompt injection where malicious content within the processed data could attempt to influence the agent's behavior. \n
- Ingestion points: Usage of
ChatCreateCompletionParams,AudioTranscribeParams, andAiSummarizeParamsinSKILL.md. \n - Boundary markers: Not present in the provided SDK usage examples. \n
- Capability inventory: Communicates with Telnyx AI APIs for inference, embeddings, and analytics. \n
- Sanitization: No explicit sanitization or input validation is demonstrated in the basic SDK examples.
Audit Metadata