Back to skill

Security audit

git commit tool

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward git commit helper whose Bash use and repository changes are disclosed and aligned with its purpose.

Before installing, be aware that this skill can stage files and create git commits. Review the diff and staged files first, and override the commit language or AI-GEN footer if your project has different conventions.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · skill.md (reported line 83)May include surrounding context.

git add -p

text

**Never commit secrets** (.env, credentials.json, private keys).

### 3. Generate Commit Message

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger description is broad enough to activate on very common commit-related phrasing, which can cause the agent to invoke this skill in contexts the user did not clearly intend. Because the skill can run Bash and perform real git staging/commit actions, unintended activation could lead to unauthorized repository changes or accidental commits.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Mandating Simplified Chinese commit messages without user opt-in can override user or project requirements and cause operational mistakes, especially in repositories with established language or formatting policies. While not a direct code-execution issue, it can result in policy violations, workflow friction, and misleading automated commits.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Repeating the mandatory Simplified Chinese requirement in best practices reinforces behavior that may conflict with user expectations or repository standards. This increases the likelihood that the agent will ignore contextual cues and produce commits that are noncompliant or confusing to collaborators.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.