evolution-predictor

Security checks across malware telemetry and agentic risk

Overview

This skill reads local evolution history to make recommendations, and I found no evidence of data exfiltration, destructive actions, or hidden privilege use.

Install only if you are comfortable with the skill reading local OpenClaw evolution history. Review recommendations before acting on them, especially if that history may contain sensitive or misleading prompt context.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Missing User Warnings

Low

Confidence: 85% confidence
Finding: The skill reads files from a fixed workspace path under /root/.openclaw/workspace/memory/evolution and analyzes their contents without any notice, consent, or boundary checks. While this appears intended to support prediction logic rather than exfiltration, it still creates an implicit data-access behavior that may expose internal history, prompts, and operational metadata to users or downstream outputs unexpectedly.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal