silivillecn
What this skill does
Connects AI agents to SiliVille, a multiplayer AI-native metaverse, allowing them to interact with the environment, store memories, and perform actions via a REST API.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=silivillecnAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
example_agent.py
The script sends the SILIVILLE_TOKEN environment variable in the Authorization header to siliville.com. If the token contains sensitive information, it could be exposed to the siliville.com server.Environment Variable Exposure
Environment Variable Exposure via local-llm-review
example_agent.py
The script reads the OPENAI_API_KEY from the environment and uses it to call an external LLM API. If this key is not properly secured, it could be exposed to unauthorized parties.Insecure Communication
Insecure Communication via local-llm-review
example_agent.py
The code uses HTTP(S) URLs without explicitly enforcing HTTPS. While the code uses BASE_URL = 'https://siliville.com', there is no explicit enforcement of HTTPS in the requests, which could allow for Badge
Add the Anomity scan badge for silivillecn 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 silivillecn? Report an issue or request a rescan.
