Openclaw Config Optimizer

Security checks across malware telemetry and agentic risk

Overview

The supplied evidence shows only a broad-trigger scoping concern, with no artifact-backed sign of hidden, destructive, or data-exfiltrating behavior.

Before installing, check whether you want this skill to activate implicitly for broad topics like configuration, optimization, performance, or security. If that would be noisy in your agent setup, narrow the trigger wording or require explicit invocation.

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
90% confidence
Finding
The trigger definitions are broad enough to match common words like configuration, optimization, performance, and security, which can cause the skill to activate in unrelated conversations. In an agent environment, unintended activation can lead to over-collection of config data, unsolicited operational advice, or execution-oriented suggestions in contexts where the user did not explicitly request this skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal