The Agent Skills Directory

[DATA_EXFILTRATION]: The script scripts/elevenlabs_tts.py transmits text data to api.elevenlabs.io to generate audio. This network operation targets the official API of a well-known service and is a core component of the skill's functionality.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by retrieving the ELEVENLABS_API_KEY from environment variables rather than hardcoding it in the source code or instructions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external content such as client emails and chat logs. However, the risk is mitigated as the skill's primary purpose is drafting responses, and it lacks high-privilege capabilities that could be exploited by embedded instructions.

client-comms-studio