Back to skill

Security audit

Skill Publisher Claw Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent publishing toolkit for Claw skills, with expected file, git, GitHub, and link-checking behavior.

Install only if you want a local toolkit that can modify and publish skill repositories. Review changes with git diff before publishing, avoid --force unless you are certain the target directory contains only intended public skill content, and do not run publish.sh from a directory with unrelated private files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
# One command to audit, fix, commit, and push a skill
#
# Usage: ./publish.sh [skill-directory] [--force]
#   --force: Skip confirmation prompts
#

set -e
Confidence
80% confidence
Finding
Skip confirmation

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.