The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or scripts. The workflow follows a logical and safe sequence for media editing.
[COMMAND_EXECUTION]: The script scripts/apply_cuts.py executes the local /usr/local/bin/screenkite CLI tool using subprocess.run with a list of arguments. This method is secure against shell injection as it does not invoke a shell to parse the command string.
[EXTERNAL_DOWNLOADS]: The skill integrates with ElevenLabs for transcription services. Audio data is sent to their official API, and the required API key is managed via a .env file as per the instructions, which is a recommended security practice. ElevenLabs is recognized as a well-known service.
[DATA_EXFILTRATION]: No evidence of unauthorized data exfiltration was found. Network activity is limited to the intended transcription service (ElevenLabs).

screenkite-transcription-cut