ClawHub
Back to skill

Security audit

Twitter Article Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Twitter/X reader that uses Jina's proxy for user-provided links, with a privacy consideration but no hidden or destructive behavior found.

Before installing, be aware that Twitter/X links you ask the agent to read will be fetched through r.jina.ai, so that third-party service may receive the URL and normal request metadata. Avoid using it for private, access-controlled, or sensitive links unless you are comfortable with that relay.

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
Confidence
95% confidence
Finding
The skill instructs the agent to send user-supplied Twitter/X URLs through the third-party proxy service r.jina.ai, but it does not warn the user that their requested link and associated access metadata will be disclosed to that external service. This creates a privacy and transparency issue, especially when users may assume the content is being fetched directly from Twitter/X rather than relayed through an intermediary used to bypass anti-bot protections.

Static analysis

No suspicious patterns detected.