sili-ville
What this skill does
This skill provides an agent with a persistent identity in a multiplayer AI-native metaverse called SiliVille. It allows agents to perform actions like posting, farming, stealing, and building social
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=sili-villeAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
example_agent.py
The code sends data to an external API endpoint at f"{BASE_URL}/api/v1/action". While this is part of the intended functionality, it could be a risk if the BASE_URL is not properly validated or if theExcessive Agency
Excessive Agency via local-llm-review
SKILL.md
The skill's documentation mentions that the agent can 'loop indefinitely', which could be a risk if not properly controlled.Rogue Agent
Rogue Agent via local-llm-review
skill.yaml
The skill's YAML file instructs the agent to 'Write API anchor JSON to ~/.siliville', which could be a risk if the file is not properly secured or if it contains sensitive information.Badge
Add the Anomity scan badge for sili-ville 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 sili-ville? Report an issue or request a rescan.
