The Agent Skills Directory

[SAFE]: No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected within the skill instructions or the accompanying Python script.
[EXTERNAL_DOWNLOADS]: The skill interacts with the well-known service openrouter.ai to generate audio content. This network activity is documented as the skill's primary purpose.
[COMMAND_EXECUTION]: The entrypoint executes a local Python script (scripts/openrouter_audio.py). Analysis of the script shows it performs legitimate operations: parsing arguments, fetching audio data via HTTP, and writing WAV files to a user-defined directory.
[DATA_EXFILTRATION]: The skill handles an API key for OpenRouter by injecting it into a child process environment variable. The key is only transmitted to the authorized openrouter.ai domain via standard HTTP headers.

audio-cog