ClawHub
Back to skill

Security audit

ClawOps

Security checks across malware telemetry and agentic risk

Overview

This is a descriptive orchestration skill with no executable payload, but it asks to coordinate installed skills, scheduling, restarts, configuration, and secrets without clear limits.

Install only if you intend to give this skill a broad coordinator role. Before using it, confirm it requires explicit approval for secrets, scheduled/background actions, restarting skills, and changing other skill behavior, preferably in an environment with limited credential and skill-management access.

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 skill description grants ClawOps sweeping authority over installed skills, dependencies, scheduling, secrets management, and event handling without defining boundaries, triggers, or approval requirements. In an agent ecosystem, this kind of unconstrained orchestration language can enable overbroad activation and privilege assumptions, increasing the risk of unintended cross-skill actions or abuse if the orchestrator is invoked in sensitive contexts.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.