The Agent Skills Directory

[SAFE]: The skill serves a legitimate purpose of helping users comply with EU AI Act labeling requirements for media content. \n- [COMMAND_EXECUTION]: The script scripts/ai-label.py executes ffmpeg and ffprobe to process media files. These executions use list-based arguments with subprocess.run() and do not invoke a shell, which effectively prevents shell injection vulnerabilities. \n- [EXTERNAL_DOWNLOADS]: All icon assets are bundled locally within the assets/ directory. The skill does not perform any network requests during execution. \n- [DATA_EXFILTRATION]: There is no evidence of sensitive file access, credential harvesting, or data exfiltration. The script only interacts with the media files specified by the user. \n- [PROMPT_INJECTION]: The instructions in SKILL.md are purely functional and do not attempt to bypass safety filters or override agent behavior.

eu-ai-label