telnyx-account-access-java

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill manages account resources through the official Telnyx Java SDK (com.telnyx.sdk:telnyx-java), which is a verified vendor library.
  • [SAFE]: Sensitive credential management is handled securely by loading API keys from environment variables using TelnyxOkHttpClient.fromEnv().
  • [PROMPT_INJECTION]: The skill handles data from external API responses (e.g., address books, IP descriptions, SSO configurations) which constitutes an indirect prompt injection surface.
  • Ingestion points: Data retrieved from methods like client.addresses().list() and client.accessIpAddress().retrieve() in SKILL.md.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are used to wrap external API content.
  • Capability inventory: Includes network access via the SDK to modify account security settings, including SSO, secrets, and IP filters.
  • Sanitization: No explicit sanitization or validation of API data is documented in the code examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:16 AM
Security Audit — agent-trust-hub — telnyx-account-access-java