ClawHub
Back to skill

Security audit

Tweet Composer

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only tweet optimization guide with no executable behavior, but users should treat its claimed X ranking details as partly estimated.

Installers should understand this skill gives tweet-writing advice based on the author's interpretation of X ranking behavior. It does not appear to access accounts or post anything, but its algorithm claims should be treated as guidance rather than verified exact scoring.

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
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s invocation guidance is broad enough to match ordinary requests for general posting or strategy advice, which can cause the agent to invoke this skill in situations where the user did not specifically ask for algorithm-based tweet optimization. That increases the chance of unnecessary context loading and over-application of the skill, though it does not directly create code execution or data exfiltration risk.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The document presents itself as derived from the 'actual code' while later acknowledging that important ranking weights are estimated rather than directly sourced. This can materially mislead users into trusting speculative guidance as authoritative, causing poor decisions or deceptive downstream outputs from the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.