ClawHub
Back to skill

Security audit

X Research by Gecho

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only X research helper that uses Gecho’s MCP tools and Chrome extension, with local result saving that users should understand before use.

Before installing, be comfortable with using Gecho’s Chrome extension and MCP server against a logged-in X session. Treat saved JSON results as potentially sensitive local files, especially on shared machines, and choose a directory you control.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 323)May include surrounding context.

md
Join the [WeCom group](https://github.com/gecho-ai/gecho-bridge/blob/main/qywx.jpg), visit [Discord](https://discord.gg/RFDVZMR6Tn), or use the [1:1 support QR code](https://github.com/gecho-ai/gecho-bridge/blob/main/wx.jpg).

## Output guidelines

For successful search:

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly saves raw X search and post-detail results to local JSON files but does not warn users that social-media content, author data, links, and replies may persist on disk beyond the session. This creates a privacy and data-handling risk, especially on shared machines or when users collect sensitive monitoring data, even though it is not an active code-execution issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.