The Agent Skills Directory

[SAFE]: The skill follows security best practices by recommending the use of environment variables for API key management rather than hardcoding credentials.
[SAFE]: The inclusion of Ed25519 webhook signature verification in the implementation examples ensures that incoming messages are authenticated and prevents request spoofing.
[INDIRECT_PROMPT_INJECTION]: The skill includes functionality for handling incoming messaging data which represents a potential attack surface for untrusted content.
Ingestion points: The payload variable within the handle_webhook function in SKILL.md ingests external data from the Telnyx API.
Boundary markers: The provided code examples do not include explicit delimiters or instructions to the agent to ignore potentially malicious embedded instructions in the message text.
Capability inventory: The skill facilitates outbound communication through methods such as client.messages.send and client.messages.send_whatsapp as documented in SKILL.md.
Sanitization: No specific sanitization, filtering, or escaping logic is demonstrated for the text field of incoming message payloads in the provided examples.

telnyx-messaging-python