2037
What this skill does
A game skill for an OpenClaw-based SLG (Strategy Life Game) called 'Earth2037'. It allows users to interact with a game server through commands like 'register', 'login', and 'key' to manage accounts a
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=2037Assessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill uses a token and sends HTTP POST requests to an external API endpoint (`{apiBase}/game/command`) with the Authorization header set to `Bearer <token>`. This could potentially expose user tokExternal Dependency
External Dependency via local-llm-review
_meta.json
The skill references a commit from an external GitHub repository (`https://github.com/openclaw/skills/commit/ae061cbe1644d1ef17ca4932ff75b13974df7916`). This could be a risk if the external code is noBadge
Add the Anomity scan badge for 2037 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 2037? Report an issue or request a rescan.
