ClawHub
Back to skill

Security audit

Zen Editorial Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed editorial review checklist for news-style submissions and does not include code, persistence, credential access, or hidden execution behavior.

Installers should understand that this skill may give moderation-style recommendations including delete/reject decisions, but it appears to only produce review reports and should still require the user or host platform to perform any real publication or deletion action.

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
94% confidence
Finding

The description contains broad trigger phrases like 'article moderation', 'editorial QA', and 'accept or reject a post', which are common everyday requests and may cause the skill to activate in contexts the user did not explicitly intend. Unintended invocation can route unrelated content through this skill's editorial decision flow, increasing the chance of incorrect moderation actions or disclosure of unnecessary review logic.

Content

No source excerpt is available for this finding.