The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data, which creates a surface for indirect prompt injection attacks.
Ingestion points: Incoming webhook payloads (r.Body) and inbound message text fields (data.payload.text) are processed by the agent in the webhook handling and message receiving flows described in SKILL.md and references/api-details.md.
Boundary markers: The skill does not define specific boundary markers or provide instructions to the agent to ignore potential instructions embedded within message content.
Capability inventory: The skill possesses network capabilities to send outbound messages through various methods like client.Messages.Send and client.Messages.SendWhatsapp.
Sanitization: The provided examples and instructions do not include steps for sanitizing or validating the content of received messages before processing.
[EXTERNAL_DOWNLOADS]: Fetches the official Telnyx Go SDK from the vendor's repository (github.com/team-telnyx/telnyx-go) for installation via the go get command.
[SAFE]: Credential management is handled securely by retrieving the API key from environment variables (os.Getenv("TELNYX_API_KEY")) rather than using hardcoded values.
[SAFE]: The skill provides clear instructions and code for verifying the authenticity of incoming webhooks using Ed25519 signatures, protecting against spoofing.

telnyx-messaging-go