The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the official Telnyx Python SDK.
Evidence: SKILL.md recommends running pip install telnyx to set up the environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Telnyx API that could contain untrusted content, potentially influencing the agent's behavior.
Ingestion points: Data is fetched in SKILL.md using methods like client.portouts.list(), client.portouts.comments.list(), and client.portouts.events.list(), which return string fields such as body (for comments), reason, and authorized_name.
Boundary markers: The provided instructions do not define specific delimiters or guidelines for the agent to distinguish between its core instructions and the data returned by the API.
Capability inventory: The skill provides methods for modifying external data, such as client.portouts.update_status() and client.portouts.comments.create() in SKILL.md.
Sanitization: There is no evidence of string sanitization, filtering, or content validation for the data retrieved from the API within the documented examples.

telnyx-porting-out-python