Aggressive Context Optimizer

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed OpenClaw optimization helper, with a caution that its broad trigger could make it activate in more situations than users expect.

Before installing, review any proposed config changes or scripts and apply them only when you are intentionally tuning OpenClaw behavior. Treat aggressive defaults as reversible recommendations, not automatic changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger description is very broad and includes many generic phrases such as high API costs, slow responses, wasteful tasks, or noisy recall, which can cause the skill to activate in contexts where aggressive configuration changes are not appropriate. Because the skill is explicitly 'aggressive and opinionated' and recommends applying scripts and config changes, unintended invocation could degrade memory quality, truncate useful context, or alter system behavior without sufficient user intent confirmation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal