atlas-argos
What this skill does
The skill is a system prompt for an AI agent named ATLAS, which is the autonomous manager of the ARGOS ecosystem. It is designed to manage a cryptocurrency trading bot (ARGOS) running on a Linux machi
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=atlas-argosAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill includes a curl command that sends a message via Telegram's API using a bot token. This could be used for data exfiltration if the BOT_TOKEN is compromised or if the skill is manipulated to Obfuscation
Obfuscation via local-llm-review
_meta.json
The skill references a commit hash from an external repository, which could be used for obfuscation or to hide malicious changes.Privilege Escalation
Privilege Escalation via local-llm-review
SKILL.md
The skill includes a reference to 'sudo', which could be used for privilege escalation if not properly controlled.Badge
Add the Anomity scan badge for atlas-argos 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 atlas-argos? Report an issue or request a rescan.
