ClawHub
Back to skill

Security audit

Claude Settings Editor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped helper for editing Claude configuration files and does not include hidden code, network behavior, or deceptive instructions.

Before installing, understand that this skill can help modify persistent Claude settings, including permissions and hooks. Use it for intentional config changes, review proposed edits before applying them, and be especially careful with changes that broaden permissions or automation hooks.

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
91% confidence
Finding

The manifest file's default prompt begins with "Help me update Claude settings," which relies on a broad everyday phrase ("Help me") rather than a narrowly scoped invocation condition. The file does not provide explicit trigger constraints or exclusion conditions, increasing the chance of unintended activation in loosely related conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.