ClawHub

Knowledge Graph

Security checks across malware telemetry and agentic risk

Overview

This skill is a scoped local helper for maintaining a workspace knowledge graph, with no evidence of hidden network access, credential use, or destructive behavior.

Install only if you want the agent to maintain persistent knowledge files under life/areas/**. Review facts before adding or superseding them, avoid storing sensitive or untrusted claims, and note that the skill needs Python 3 plus local file read/write access even though permissions are not explicitly declared.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly instructs the agent to read and write files under `life/areas/**` and to invoke a bundled Python script that performs those updates, but the skill declares no permissions. This creates a capability/permission mismatch that can bypass expected review and containment controls, making unauthorized filesystem modification easier if the skill is invoked in a broader environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal