ClawHub
Back to skill

Security audit

Ai Csuite

Security checks across malware telemetry and agentic risk

Overview

This is a local business decision helper that transparently reads company context and writes a local decision file, with no evidence of hidden network, credential, or destructive behavior.

Safe to install for local strategy-decision drafting. Review or replace the sample company config before use, avoid putting secrets into the YAML or generated markdown, and choose an output path carefully if working in a shared repository or workspace.

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
Findings (1)

Missing User Warnings

Low
Confidence
75% confidence
Finding
The skill writes output files locally (`logs/latest-decision.md`) and relies on local config inputs, but the user-facing description does not prominently disclose this upfront. That can lead to surprise local state changes, unintended persistence of sensitive business strategy content, or accidental overwrite/exposure of generated decision artifacts in shared workspaces.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.