Security checks across malware telemetry and agentic risk
This skill does what it claims: it generates and edits AI videos using user-provided prompts, media, API keys, cloud providers, and FFmpeg, with no evidence of hidden persistence, exfiltration, or destructive behavior.
Install this in a virtual environment, keep provider API keys limited and private, monitor API usage for costs, and avoid sending confidential prompts, scripts, images, audio, or videos unless the providers' terms and retention policies are acceptable. Choose output paths carefully because FFmpeg commands use overwrite behavior for selected outputs.
# Download video
video_path = self.output_dir / f"video_{int(time.time())}.mp4"
video_data = requests.get(video_url).content
with open(video_path, 'wb') as f:
f.write(video_data)openai>=1.0.0 replicate>=0.20.0 requests>=2.31.0 pillow>=10.0.0
openai>=1.0.0 replicate>=0.20.0 requests>=2.31.0 pillow>=10.0.0 python-dotenv>=1.0.0
openai>=1.0.0 replicate>=0.20.0 requests>=2.31.0 pillow>=10.0.0 python-dotenv>=1.0.0
openai>=1.0.0 replicate>=0.20.0 requests>=2.31.0 pillow>=10.0.0 python-dotenv>=1.0.0
replicate>=0.20.0 requests>=2.31.0 pillow>=10.0.0 python-dotenv>=1.0.0
66/66 vendors flagged this skill as clean.