telnyx-ai-inference-javascript

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the telnyx package from npm, which is the official SDK from the vendor.\n- [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by exposing parameters that allow the insertion of system instructions or instructions into the AI context. \n
  • Ingestion points: The system_prompt field in the /ai/summarize endpoint and the instructions field in the /ai/conversations/insights endpoint in SKILL.md.\n
  • Boundary markers: There are no explicit markers or delimiters defined in the examples to isolate untrusted data from the instructions.\n
  • Capability inventory: The skill allows the agent to interact with language models, retrieve conversation history, and generate summaries via the Telnyx API.\n
  • Sanitization: The provided code examples do not include input validation or sanitization for the instruction fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:16 AM
Security Audit — agent-trust-hub — telnyx-ai-inference-javascript