twilio-send-message
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (such as recipient numbers and message bodies) which is then used in API calls to Twilio.
- Ingestion points: The
body,to, andmedia_urlparameters inSKILL.mdexamples ingest data that may originate from external sources. - Capability inventory: The skill utilizes network capabilities via the Twilio SDK to send messages and media.
- Boundary markers: The provided snippets do not include explicit boundary markers or instructions to ignore embedded commands within the message body.
- Sanitization: No sanitization or validation logic is present in the examples to filter potential injection attacks within the message content.
Audit Metadata