oh-my-git-commit

• Outcome: Review
• Latest audit: Sep 16, 2026 · 8:17 AM UTC
• Version: 1.0.0

Overview

This git commit helper is mostly coherent, but its broad triggers and lack of explicit confirmation before staging or committing create a real risk of unintended repository changes.

Install only if you want a Bash-powered git commit assistant. Before letting it act, require it to show git status, the exact files to stage, and the final commit message; avoid using broad natural-language prompts when you do not intend to create a commit.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Credential Access

High

• Category: Privilege Escalation

Content

git add -p
```

**禁止提交机密信息**（.env、credentials.json、私钥等）。

### 3. 生成 Commit Message

• Confidence: 70% confidence
• Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Shadow Command Trigger

Medium

• Category: Trigger Abuse
• Confidence: 89% confidence
• Finding: Using a trigger that conflicts with a built-in command creates ambiguity over which handler will execute, which can lead to unexpected or unintended behavior. In a repository-modifying skill, that ambiguity is dangerous because users may invoke the built-in command semantics but instead trigger custom staging and commit logic.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The condition "用户要求提交更改" is ambiguous and lacks precise boundaries, so the skill may interpret general discussion about submitting or saving changes as authorization to run Git operations. This increases the chance of unintended staging or commits based on conversational context rather than explicit user consent.

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The trigger phrase "commit" is extremely broad and can match ordinary conversation, causing the skill to activate when the user did not intend to perform a Git commit. In a skill that can stage files and create repository history, accidental invocation can lead to unintended source-control actions or disclosure of sensitive diffs to the agent.

Natural-Language Policy Violations

Medium

• Confidence: 98% confidence
• Finding: The instruction "message 使用中文撰写" forces a specific language for output, and the examples reinforce that requirement. There is no opt-in, user choice, or documented regional justification, which makes this a natural-language locale policy violation under the stated rules.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 92% confidence
• Finding: The trigger "提交" is too short and generic, making accidental activation likely during normal Chinese conversation about submitting, uploading, or turning in work. Because the skill can inspect diffs, stage files, and create commits, this broad trigger expands the attack surface for unintended repository changes.

Static analysis

No suspicious patterns detected.