ClawHub
Back to skill

Security audit

Moin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent tweet-writing guide that uses disclosed web research and does not install code, persist state, post content, or access accounts.

Install is reasonable for public-facing tweet drafting. Before using it, avoid sharing unreleased strategy, client names, private metrics, or sensitive personal details unless you are comfortable with those details being used in web searches; ask the agent to use generalized search terms when needed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 mandates use of WebSearch on the user's niche/topic before producing output, but it does not warn the user that their prompt content may be sent to third-party search providers. If the user's topic includes confidential business strategy, unreleased campaigns, client names, or sensitive personal context, this requirement can cause unintended external disclosure. In this skill's context, the risk is elevated because the research step is framed as mandatory for every request, increasing the likelihood of routine data transmission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.