hive-task-router
What this skill does
Intelligent task routing system that identifies task types and routes to optimal models with appropriate execution mode. Supports any AI model provider via environment variables.
github/leoyeai - Code Injection - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=hive-task-routerAssessments (1)
Code Injection
Code Injection via local-llm-review
router.sh
The script contains logic to route tasks based on keywords and execute with specific models, but no direct evidence of malicious behavior. However, the script's ability to execute with different modelBadge
Add the Anomity scan badge for hive-task-router 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 hive-task-router? Report an issue or request a rescan.
