telnyx-ai-inference-curl
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for processing untrusted external data which could potentially contain malicious instructions targeting the AI model.
- Ingestion points: The skill facilitates processing of local files and remote website content through the
/ai/audio/transcriptions,/ai/summarize, and/ai/embeddings/urlendpoints as documented inSKILL.md. - Boundary markers: No explicit delimiters or boundary markers are demonstrated in the curl payloads to isolate untrusted user data from system instructions.
- Capability inventory: The skill demonstrates network communication capabilities specifically targeting the official vendor API at
api.telnyx.com. - Sanitization: The provided examples show data being passed to the API without visible client-side sanitization or filtering.
- [SAFE]: The skill follows security best practices by using environment variables for authentication and interacts exclusively with the legitimate vendor infrastructure. No code obfuscation, persistence mechanisms, or unauthorized privilege escalation patterns were found.
Audit Metadata