omniwire
What this skill does
Infrastructure management for AI agent swarms, including mesh control, SSH, Docker, firewall management, and more.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=omniwireAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The metadata section claims 'No data leaves your network.' This is a strong claim that could be a false assurance if the implementation does not enforce it. Further inspection of the actual code wouldConfiguration Management
Configuration Management via local-llm-review
SKILL.md
The skill references encrypted secrets in ~/.omniwire/secret.key. If this file is not properly secured, it could be a risk. However, this is a standard practice and not inherently malicious.Badge
Add the Anomity scan badge for omniwire 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 omniwire? Report an issue or request a rescan.
