twilio-messaging-services
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard instructional content for Twilio Messaging Services. All code snippets utilize the official 'twilio' SDK and adhere to best practices for handling sensitive credentials via environment variables (TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN).
- [INDIRECT_PROMPT_INJECTION]: The skill provides functionality to send messages where the message 'body' content is ingested from the agent's context. While this is the primary purpose of the skill, it represents a potential surface for indirect prompt injection if untrusted data is included in the message body without sanitization.
- Ingestion points: The 'body' parameter in
client.messages.createfunctions (SKILL.md). - Boundary markers: None present in the provided code snippets to delimit untrusted content within the message body.
- Capability inventory: The skill uses the Twilio REST API to perform network operations and send outbound communications (SKILL.md).
- Sanitization: No explicit sanitization or validation of the message body content is shown in the examples.
Audit Metadata