Coordinator Agent
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed OpenClaw fleet-monitoring coordinator that reads configured workspaces, sends briefings, and can retrigger cron jobs when the user enables that behavior.
Install only if you are comfortable with a coordinator reading the configured agent workspaces and sending summaries to external messaging services. Use dedicated scoped credentials, avoid copying broad auth profiles, exclude workspaces containing secrets, and leave self-healing disabled unless repeated cron execution is safe.
Publisher note
v1.2.0 adds prominent Security Warning section addressing all 3 Medium findings from SkillSpector audit (Missing User Warnings x2, Session Persistence). Self-healing now warns about idempotence. Scoped credentials recommended as Option A with auth-profile copy as Option B with warning. Redaction recommendation added. No SOUL.md in package per ClawdHub convention. SKILL.md only.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
60/60 vendors flagged this skill as clean.