ClawHub
Back to skill

Security audit

@_FORAB Tweet Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language tweet drafting skill with no code, tools, persistence, credential handling, or automatic posting behavior.

Install only if you want an agent to draft Chinese Twitter/X-style content modeled on @_FORAB. Review generated political, financial, and crypto commentary before use, especially for accuracy and impersonation or attribution concerns, but the artifact itself does not request sensitive access or perform posting.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description states the skill generates tweets in Chinese style and all examples/instructions are written only in Chinese, which implies a fixed language behavior. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified, which is not present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.