ClawHub
Back to skill

Security audit

Yeet

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises, but it can broadly stage, commit, push, and open a GitHub PR with limited scoping safeguards.

Review `git status` and the exact diff before using this skill. It is best used only in repositories where you are comfortable publishing all staged and untracked changes, and where branch creation, dependency installation, pushing to origin, and draft PR creation are intended.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly performs repository-modifying and network operations (`git add -A`, `git commit`, `git push`, and `gh pr create`) but does not require a clear user confirmation immediately before making those changes. Because it stages everything and may create a branch, push to origin, and open a PR in one flow, a user could trigger unintended publication of local changes or sensitive files, especially if they do not fully understand the scope of the operation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.