ClawHub
Back to skill

Security audit

Caveman Commit

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives formatting rules for concise commit messages and does not install code, run commands, or change files.

Install this if you want the agent to prefer terse Conventional Commit messages. Be aware that the skill may be selected around staged changes or common commit-message requests, so avoid using it in repositories where staged diffs contain sensitive content you do not want summarized into chat.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises broad trigger phrases and explicitly states it auto-triggers when staging changes, which can cause unintended activation outside a clear user request. In practice, this may hijack normal workflow context, inject unsolicited output, or cause the agent to act on sensitive diff content when the user did not intentionally invoke this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.