ClawHub
Back to skill

Security audit

Caveman Review

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes how code review comments are written and does not add hidden execution, data access, persistence, or mutation authority.

Install this if you want very terse PR feedback by default. Be aware it may activate during pull request reviews unless you say "stop caveman-review" or "normal mode," and use normal review style when fuller security or architecture explanations are needed.

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 declares it auto-triggers for broad pull request review contexts, which can cause it to activate without explicit user intent. Because this skill changes output style and review behavior, an overbroad trigger can unexpectedly steer security-sensitive review workflows or suppress fuller explanations except in carve-out cases, increasing the chance of missed nuance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.