ClawHub
Back to skill

Security audit

Clawhub Publish 146256

Security checks for vulnerabilities and agentic risk

Overview

This skill matches its article-illustration purpose, but users should expect it to create image-related files and update the article with image links.

Install this only if you want the agent to create an illustrations directory, save prompt/outline/image files, read scoped Baoyu preference files if present, and update the target article with Markdown image links. Consider working on a copy if you do not want in-place article edits.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs writing multiple files to disk and modifying the article by inserting image references, but it does not clearly warn the user that source content will be changed or require explicit confirmation before doing so. In an agent setting, silent filesystem writes and source edits can cause unintended data loss, repository noise, or modification of sensitive working files, especially if the user expected analysis-only behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.