ClawHub
Back to skill

Security audit

git-commit-message-helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small commit-message helper that only suggests text from staged git changes and does not request network, write, commit, push, persistence, or credential access.

Install if you want help drafting conventional commit messages. Be aware the trigger wording is broad, so confirm the agent is using staged git changes or a pasted diff/stat before relying on the suggested message.

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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation example "write a commit message" is generic natural language and the file does not provide exclusion conditions or tighter scope beyond the surrounding description. This could cause unintended invocation when a user wants general writing help rather than this specific staged-diff workflow.

Content

No source excerpt is available for this finding.