watch
What this skill does
Video processing and transcription using AI APIs (Groq/OpenAI Whisper)
github/bradautomates - Data Exfiltration - 14.9k stars
Threat analysis
Skill info
pkg:github/bradautomates/claude-video@83da59f?skill=watchAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/whisper.py
Uploads audio to Groq or OpenAI Whisper API endpoints without explicit user confirmation or encryption guaranteesInsecure Configuration
Insecure Configuration via local-llm-review
scripts/setup.py
Creates ~/.config/watch/.env file without enforcing strict permissions (could be readable by other users)Badge
Add the Anomity scan badge for watch 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 watch? Report an issue or request a rescan.
