Olares Dashboard (olares-cli dashboard)
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent maintenance guidance, but it includes a review helper that defaults a nested agent to full sandbox bypass and other maintainer commands with high-impact write authority.
Install only if you need ClawHub/Convex maintainer workflows and trust the local repo context. Before using the autoreview helper, prefer `--no-yolo` or `AUTOREVIEW_YOLO=0` unless full sandbox bypass is explicitly acceptable. Use moderation and proof-publishing commands only with the intended GitHub/ClawHub credentials and after confirming the exact target and effect.
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
65/65 vendors flagged this skill as clean.