telnyx-ai-inference-java
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the official Telnyx Java SDK (com.telnyx.sdk:telnyx) as a dependency for its functionality. This is a trusted resource provided by the skill's author.
- [PROMPT_INJECTION]: The skill provides tools that handle user-supplied content and system instructions for LLM interaction (e.g., chat completions and insight templates). While this is the intended purpose, it represents an inherent surface for indirect prompt injection if processing untrusted data.
- Ingestion points: User-provided strings in
ChatCreateCompletionParams,InsightCreateParams, and external files/URLs viaAiSummarizeParamsandEmbeddingUrlParams. - Boundary markers: None explicitly defined in the code snippets; the skill assumes standard API parameterization.
- Capability inventory: The skill allows reading files from storage buckets, crawling URLs for embedding, and generating LLM responses via the Telnyx API.
- Sanitization: Input sanitization and safety filtering are assumed to be managed by the underlying Telnyx AI service infrastructure.
Audit Metadata