ClawHub

skill-creator-canonical

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent skill-authoring helper that edits, validates, packages, and optionally publishes skill files with no evidence of hidden data access or exfiltration.

Install this only if you want an agent to help author and package skills. Expect it to modify target skill folders and run its bundled Python validators and packager. Review generated files, .clawhubignore contents, version metadata, and publish command details before allowing any public release.

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
95% confidence
Finding
The skill instructs the agent to read and write files and execute shell commands (`python3`, `clawhub`) but does not declare permissions or constrain scope. This creates a real capability/intent mismatch: a caller or runtime may not realize the skill can modify the filesystem, package artifacts, or publish releases, which increases the chance of over-privileged or unsafe execution.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal