ClawHub
Back to skill

Security audit

rules-eval

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only rules audit guide with one minor overbroad-trigger concern, but no hidden execution, persistence, credential use, or destructive behavior.

Installers should expect this skill to help review Claude Code rule files. Review the trigger terms if you want to avoid it activating during unrelated conversations about generic evaluation or validation, but the inspected artifacts do not show high-impact or hidden behavior.

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 trigger list uses generic terms like "evaluation", "rules", and "validation", which can cause the skill to be invoked in contexts unrelated to Claude rule auditing. This increases the chance of unintended activation, potentially steering workflows unexpectedly or displacing a more appropriate skill, but it does not by itself enable code execution or data exfiltration.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.