telnyx-api
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements logic for processing incoming SMS/MMS messages via webhooks (e.g., in SKILL.md, references/webhooks.md, and assets/examples/webhook-handler.ts). These examples ingest untrusted user text (event.payload.text) and interpolate it directly into conversation state machines or response handlers. The absence of boundary markers or sanitization in these patterns creates a surface for indirect prompt injection, where a malicious message sender could attempt to influence the agent's behavior.
- Ingestion points: Webhook payload text (event.payload.text) in SKILL.md, assets/examples/webhook-handler.ts, and references/webhooks.md.
- Boundary markers: Absent in the provided examples.
- Capability inventory: Includes network operations (sendSMS, axios.post, fetch) and conversation state management across multiple scripts.
- Sanitization: Absent in the provided code patterns.
Audit Metadata