ClawHub
Back to skill

Security audit

Content Repurposer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple content-repurposing writing skill with broad but purpose-aligned input handling and no code execution, persistence, or sensitive access.

Before installing, users should understand that the skill may activate for broad content transformation requests; avoid providing confidential unpublished material unless you are comfortable having it rewritten into multiple public-facing formats.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The README presents activation examples like "Repurpose this blog post" and "Turn my podcast transcript into..." as free-form requests, but it does not define any explicit trigger phrases, boundaries, or exclusion conditions. This makes the skill's invocation scope broad and potentially overlapping with ordinary content-editing requests, increasing the chance of unintended activation.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The markdown says to 'Accept any source format' and includes very broad examples such as 'Raw notes or bullet points' and 'Even a single tweet or idea.' This makes the invocation scope unusually open-ended and does not provide exclusion conditions or negative examples, increasing the chance of unintended use for loosely related requests.

Static analysis

No suspicious patterns detected.