ClawHub
Back to skill

Security audit

conventional-commits

Security checks for vulnerabilities and agentic risk

Overview

This skill only helps draft Conventional Commit messages from a git diff and does not install code, persist itself, or perform repository mutations.

Installers should understand that the skill may activate on vague uses of the word "commit"; use it for commit-message drafting and review the generated message before using it.

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

Medium
Confidence
91% confidence
Finding
The trigger description says to use the skill whenever the user asks to write, draft, or improve a commit message, or says "commit," which is an overly broad everyday phrase. Broad triggers can cause the skill to activate in unintended contexts, potentially overriding more appropriate skills or causing the agent to act on ambiguous requests without sufficient user intent.

Static analysis

No suspicious patterns detected.