telnyx-ai-inference-curl
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous
curlcommand examples to interact with the Telnyx API. These commands are intended for developers to copy and execute in their terminal to test and integrate Telnyx services. - [DATA_EXFILTRATION]: The skill includes examples for uploading local files and processing external URLs through the Telnyx infrastructure. These actions are standard for the provided services (such as transcription and summarization) and use official Telnyx endpoints (
api.telnyx.com). - [PROMPT_INJECTION]: The skill exposes surfaces for indirect prompt injection by processing external data from sources like chat messages, uploaded documents, and web pages.
- Ingestion points:
SKILL.md(via endpoints such as/ai/chat/completions,/ai/summarize, and/ai/embeddings/url). - Boundary markers: No specific delimiters or boundary warnings are included in the provided shell command examples.
- Capability inventory: Shell command execution via
curland network communication with Telnyx APIs. - Sanitization: No sanitization or input validation logic is present in the provided documentation examples.
Audit Metadata