twelvelabs
What this skill does
The skill is a CLI tool that wraps the Twelve Labs API for video understanding tasks, enabling video upload, indexing, structured briefs, embeddings, and local clip cutting. It is designed to be used
github/mvanhorn - Data Exfiltration - 1.9k stars
Threat analysis
Skill info
pkg:github/mvanhorn/printing-press-library@5a78746?skill=twelvelabsAssessments (1)
Data Exfiltration
Data Exfiltration via local-llm-review
internal/cli/auth.go
The CLI provides instructions for obtaining a credential from 'https://playground.twelvelabs.io/dashboard/api-keys' and setting the 'TWELVELABS_X_AP' environment variable. While this is a legitimate pBadge
Add the Anomity scan badge for twelvelabs 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 twelvelabs? Report an issue or request a rescan.
