ClawHub
Back to skill

Security audit

Alpha Feed Creator Free

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill is mainly a disclosed X/Twitter AI-news collection and local report-writing workflow, with some confusing template text but no artifact-backed malicious behavior.

Install only if you are comfortable with an agent reading a local configuration file, accessing X/Twitter through available API credentials or a browser login session, and writing Markdown reports/logs to your configured notes path. Review or narrow the confusing SEO trigger text before relying on automatic skill activation.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description does not clearly warn up front that it will access external content sources, may use browser/API mechanisms, and will write files locally. Because the skill is granted read and exec tools and explicitly writes Markdown output into local paths, insufficient disclosure can lead to unintended exposure of local data paths, unwanted file creation, or user surprise about external platform access.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

L036 明确写明免费版的“报告推送”能力不支持，但 L038 又以“这些能力基于 input_params/output_format 实现，支持创建/查询/修改/删除等操作模式”笼统覆盖全文能力模块，容易让人理解为包括推送能力也可被操作。该文档内部对能力边界的表述相互矛盾，可能误导代理执行超出免费版范围的操作。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

该技能整体描述为从 X 平台采集 AI 内容并生成日报，但 L096-L106 却写成“需要SEO优化、关键词分析、排名提升、搜索流量优化时使用”，这与前文定义的内容采集用途明显不一致。这不是简单遗漏，而是主动把技能适用条件描述成另一类产品能力。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad and ambiguous, which can cause the agent to invoke this skill in unrelated contexts such as SEO or ranking requests. In a skill with exec permission and browser/API collection behavior, overbroad activation increases the chance of unintended local file writes, unnecessary browsing, or collection of user/environment data without clear intent.

Content

No source excerpt is available for this finding.