ClawHub
Back to skill

Security audit

X Article Editor

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing helper for drafting and reviewing X Articles, with no code execution, persistence, credential access, or data exfiltration behavior found.

Install this if you want a structured X Article drafting and review workflow. Be aware it strongly enforces a two-part output format and includes sample prompts focused on French and English; override it explicitly if you need another format, another language, citations, or disclosure of AI/tool use.

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
  • 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
Findings (2)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description says it should turn a topic or draft into an X Article, but it does not clearly define when the skill should or should not be invoked. In an agent environment, this ambiguity can cause the skill to activate on loosely related writing tasks, leading to inappropriate application of its rigid output format and hidden assumptions, which may override user intent or interfere with safer, more relevant skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file is explicitly framed as "Quick prompts (FR/EN)" and several prompt variants are labeled or constrained as French or English modes, such as "Write-from-brief (FR)/(EN)" and "Edit mode (FR)/(EN)". Although the brief includes a "Language: (optional)" field in two sections, the overall prompt set still prescribes only FR/EN variants rather than clearly offering unrestricted language choice, which may conflict with a language/locale neutrality policy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.