telnyx-ai-inference-java

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official Telnyx Java SDK repository at github.com/team-telnyx/telnyx-java. This is a vendor-owned resource used for standard installation procedures.
  • [INDIRECT_PROMPT_INJECTION]: The skill implements several endpoints that process untrusted external data, creating a potential surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the context via ChatCreateCompletionParams messages, EmbeddingSimilaritySearchParams queries, InsightCreateParams instructions, and AiSummarizeParams file content.
  • Boundary markers: The provided Java snippets do not explicitly show the use of delimiters or 'ignore' instructions for the processed data, which is typical for SDK examples.
  • Capability inventory: The skill uses network operations to communicate with Telnyx API endpoints for chat completion, document embedding, and summarization.
  • Sanitization: There is no evidence of explicit sanitization or filtering of input strings within the code examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:10 AM