ClawHub
Back to skill

Security audit

AI Code Review RiskRadar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown-only code review helper with broad but purpose-aligned triggers and no hidden execution behavior.

Before installing, understand that this skill may be invoked for many code review, testing, security, and release-readiness prompts. Use it on repositories and diffs you are comfortable letting your agent inspect, especially when proprietary code or sensitive configuration may be present.

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
Confidence
95% confidence
Finding
The trigger list is unusually broad and overlaps with many common engineering, QA, and security review tasks, which can cause this skill to activate in contexts beyond its intended scope. Over-broad activation increases the chance that users or orchestrators invoke the skill on sensitive code, release, or security-review workflows without clear user intent, expanding attack surface for prompt injection or unsafe automation if the wider system auto-routes by trigger.

Static analysis

No suspicious patterns detected.