ClawHub
Back to skill

Security audit

Content Repurposer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward content-repurposing assistant that reads user-provided source material and formats it for social platforms without hidden execution, persistence, or posting authority.

Installers should understand that this skill may fetch URLs or read file paths they provide so it can repurpose that content. It does not post to social platforms or modify accounts, but users should avoid giving it private documents unless they want that content summarized and transformed.

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 skill advertises very broad trigger phrases such as "repurpose," "create a thread," and "adapt for LinkedIn," which can match many ordinary writing or summarization requests beyond the narrow intended use case. In an agent routing system, this can cause over-selection of the skill, leading it to fetch URLs, read files, or reshape content in contexts where a more appropriate or safer skill should handle the request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.