telnyx-import-vapi
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides comprehensive code examples including shell commands (curl) and implementation snippets for multiple SDKs (Python, JavaScript, Go, Java, and Ruby) to interact with official vendor APIs.
- [DATA_EXFILTRATION]: The skill performs network operations targeting the vendor's official API endpoints at
api.telnyx.com. It requests user-provided API keys for both Telnyx and Vapi to facilitate migration, explicitly recommending that the Vapi key be stored within the Telnyx platform's secure integration secrets manager rather than being handled as a raw string. - [PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by importing assistant instructions and configurations from a third-party provider (Vapi) into the Telnyx AI Assistant ecosystem.
- Ingestion points: External assistant configuration data is retrieved from Vapi via the Telnyx import endpoint as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or "ignore previous instruction" wrappers for the ingested content.
- Capability inventory: The skill allows for the creation and configuration of AI assistants and the execution of network requests to external APIs as seen in SKILL.md.
- Sanitization: The provided documentation does not specify sanitization or validation protocols for content imported from the external provider.
Audit Metadata