The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data through the text parameter, creating a potential surface for indirect prompt injection.
Ingestion points: text parameter in the generate method and CLI commands within SKILL.md.
Boundary markers: No specific delimiters or boundary markers (like XML tags or clear separators) are suggested in the documentation to isolate input text.
Capability inventory: The skill is capable of performing network API requests to the Telnyx TTS service; it does not exhibit file-system writes or arbitrary command-execution capabilities based on the processed text.
Sanitization: No explicit input validation or sanitization is described in the provided examples.
[SAFE]: The skill follows secure credential management practices by retrieving the API key from the environment (TELNYX_API_KEY).
[SAFE]: The installation of the telnyx Python package is a legitimate dependency provided by the vendor.

telnyx-tts-python