twilio-api
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for receiving and processing incoming SMS/MMS message bodies (e.g.,
req.body.Body), which creates an ingestion surface for untrusted external data. - Ingestion points: Webhook examples in
SKILL.md(Quick Reference #4 and Production Pattern #1) demonstrate reading theBodyparameter from incoming POST requests. - Boundary markers: The provided examples do not include specific delimiters or system instructions to prevent an AI from executing commands that might be embedded in the incoming message body.
- Capability inventory: The skill enables significant capabilities including outbound SMS/MMS sending, voice call management, and arbitrary HTTP requests using the
twiliolibrary and Node.jshttpsmodule. - Sanitization: The skill includes high-quality security patterns for XML character escaping (Production Pattern #4) and HMAC-SHA1 signature validation (Quick Reference #5 and #6) to ensure the integrity and safety of the communication flow.
Audit Metadata