ClawHub
Back to skill

Security audit

Git Commit Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown-only commit-message helper with no code, install hooks, persistence, or hidden data handling.

Installers should expect this skill to help draft commit messages and PR descriptions from code changes. Review generated text before using it, and be aware that broad natural-language prompts may activate it even when a more explicit commit-helper invocation would be clearer.

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
  • 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 (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrase at line 24 is very broad and resembles an ordinary conversational request a user might make in many coding contexts. This can cause unintended skill activation, injecting the skill's behavior when the user did not explicitly choose it and potentially interfering with surrounding workflows or agent decision-making.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The invocation examples are ambiguous and overlap with normal developer requests like analyzing code changes or generating descriptions. In an agent environment, this increases the chance of accidental routing to the skill, which may expose code diffs or alter agent behavior without clear user intent.

Natural-Language Policy Violations

Low
Confidence
75% confidence
Finding
The natural-language instructions and usage documentation are presented only in Chinese, which imposes a locale/language constraint without any visible opt-in or alternative. The policy allows language constraints when users are given a choice or the limitation is clearly justified, neither of which is documented here.

Static analysis

No suspicious patterns detected.