ClawHub
Back to skill

Security audit

git-commit-helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward commit-message helper that reads git diffs and suggests Conventional Commit text without hidden networking, persistence, or unrelated access.

Installers should understand that this skill may read local git diffs, which can include source code or secrets accidentally present in changes. Review the generated commit command before letting an agent run `git commit -m`.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
This is a mismatch because the declared purpose is commit message generation, but the provided code only performs diff analysis and returns structured metadata. While the suggested type and scope could support commit message generation, the primary behavior shown does not actually generate a commit message or Conventional Commit string. There is no hidden external access or unrelated trigger behavior in the code, but the core functionality is materially narrower and different from the description.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description says to use the skill when the user asks "help me commit," which is a broad natural-language phrase that can overlap with ordinary conversation and may cause unintended invocation. Although other examples are specific, this phrase is not narrowly constrained enough on its own.

Static analysis

No suspicious patterns detected.