ClawHub
Back to skill

Security audit

Git Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Git helper description with no bundled executable code, persistence, hidden behavior, or unrelated data access.

Install only if you want the agent to help with Git operations. Treat push, pull, and branch management as state-changing actions: review the target repository and remote before asking the agent to run them.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises wrappers for git pull, git push, and branch operations without warning that these commands can change repository state, merge remote changes, create or switch branches, or send local commits to remote servers. In an agent setting, the lack of disclosure can lead users to invoke mutating or networked operations unintentionally, increasing the chance of data leakage or accidental repository modification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.