ClawHub
Back to skill

Security audit

x_management

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only X/Twitter workflow skill that emphasizes drafts, account checks, and explicit approval before posting.

Install this only if you intend to pair it with the X plugin and are comfortable letting the agent read account context and prepare drafts. Review every draft carefully before approving, especially when using multiple X accounts or media uploads, because publishing affects a live public account.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 127)May include surrounding context.

md
## Safety boundaries
- do not publish automatically
- do not assume approval from conversational enthusiasm
- do not like/repost/bookmark autonomously unless the user explicitly asks
- do not DM from this workflow
- if publish or read capabilities fail, explain the actual failure clearly

Static analysis

No suspicious patterns detected.