ClawHub

GitFlow

Security checks across malware telemetry and agentic risk

Overview

This skill is not malicious, but it can push code and interact with CI/CD systems using the user's GitHub or GitLab access without enough confirmation and scope guidance.

Install only if you want an agent to help run git push and GitHub/GitLab CI commands. Require confirmation before every push or CI rerun, verify the remote and branch, avoid using broad tokens, and fetch full CI logs only when you are comfortable exposing their contents in the agent session.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README states the skill will automatically push code and monitor CI/CD across GitHub and GitLab, but it does not warn users that invoking the skill may modify remote repositories. Automatic pushes are security-sensitive because they can publish unintended changes, trigger deployment pipelines, leak secrets committed by mistake, or alter protected project history if misused.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly promotes automatic pushing of local commits to remote repositories but does not present any warning, confirmation, or scope limitation around modifying remote state. In an agent context, this is risky because an automated workflow could unintentionally publish unreviewed code, secrets, or destructive changes to shared branches, causing integrity and deployment issues.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documentation encourages fetching pipeline status, URLs, and logs from GitHub and GitLab without warning that CI/CD logs may contain secrets, tokens, internal URLs, artifact paths, or other sensitive operational data. In an agent-assisted environment, automatically retrieving and displaying those logs increases the risk of inadvertent exposure to the user, chat history, or downstream tooling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal