Skills
skills/team-telnyx/telnyx-ext-agent-skills/telnyx-ai-assistants-java/Gen Agent Trust Hub

telnyx-ai-assistants-java

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes surfaces for indirect prompt injection where untrusted data could influence agent behavior.
  • Ingestion points: The content parameter in AssistantChatParams and the instructions parameter in AssistantCreateParams (documented in SKILL.md) are the primary entry points for external data.
  • Boundary markers: Absent. The examples do not demonstrate the use of delimiters or specific safety instructions to isolate user input from system prompts.
  • Capability inventory: The skill possesses the capability to send SMS via sendSms, manage assistant configurations, and interact with the Telnyx API as seen in SKILL.md and references/api-details.md.
  • Sanitization: Absent. There is no evidence of input validation or sanitization before data is passed to the SDK methods.
  • [EXTERNAL_DOWNLOADS]: The skill requires the com.telnyx.sdk:telnyx-java library via Maven or Gradle. This is an official dependency provided by Telnyx, a well-known technology service provider, and is considered safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:52 PM