video-use
What this skill does
Video editing and manipulation using AI agent instructions
github/browser-use - Data Exfiltration - 20.5k stars
Threat analysis
Skill info
pkg:github/browser-use/video-use@92c2b34?skill=video-useAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
helpers/transcribe.py
The script extracts audio from a video and uploads it to the ElevenLabs Scribe API (https://api.elevenlabs.io/v1/speech-to-text). This represents a data exfiltration risk as audio data is being sent tSecrets Management
Secrets Management via local-llm-review
helpers/transcribe.py
The script attempts to load an API key from a .env file or environment variables. If the .env file is not properly secured, this could lead to exposure of sensitive credentials.Badge
Add the Anomity scan badge for video-use to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of video-use? Report an issue or request a rescan.
