ClawHub
Back to skill

Security audit

Social Creative Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed social-content drafting helper that saves drafts only with permission and does not auto-post or run bundled code.

Install if you want help drafting social posts from approved ideas. Review generated claims and disclosures before publishing, and only approve saving drafts or proposal events when they fit your project workflow.

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)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The instruction specifies '标题+正文+tags for a 小红书 note' and 'delivered as paste-ready 中文 copy,' which imposes a specific language choice in the workflow. While this may be platform-norm motivated, the file does not explicitly say the user can opt into another language or confirm the locale preference.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.