Back to skill

Security audit

Blog 一文多发

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only marketing skill that converts FridayParts blog summaries into platform-specific social posts, with no hidden execution, persistence, credential access, or data exfiltration behavior found.

Review generated repair or fault-diagnosis posts before publishing, especially where safety or equipment damage is involved, and confirm that the English-only North American positioning and the configured model match your intended GetClawHub workspace settings.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (13)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description and operating instructions are written entirely in Chinese and present the workflow as the default way to use the skill, with no indication that users can choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The 'Use when' guidance is vague and does not clearly bound when the skill should or should not be invoked. Poorly defined activation scope can lead to unintentional routing of unrelated tasks into this skill, increasing the risk of inappropriate outputs, user confusion, and mishandling of safety-sensitive maintenance content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list is broad enough to activate on generic rewriting or content-editing requests, which can cause the skill to run outside its intended scope. That increases the chance of accidental prompt capture, unintended transformation of unrelated user content, or misuse in contexts where the skill's platform-specific output and assumptions are inappropriate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This skill generates public-facing social copy from technical maintenance content yet lacks a clear warning that outputs may require human review for technical accuracy and safety. Because the content can discuss diagnostics, failure causes, and repair scenarios, omission of a review warning may cause users to publish misleading or unsafe advice that readers could act on.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction "全部英文(受众是北美用户)" forces a specific language for all outputs. Under the policy, language constraints should either be optional for the user or clearly documented as a justified locale-specific limitation; here the file does not present it as a user opt-in choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents the skill context in Chinese, but all platform output examples are written in English and there is no indication that the user can choose the output language. That creates a natural-language locale policy concern because it implicitly forces a language without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The checklist repeatedly requires platform content to be written in English, such as '120-150 字英文', '60-80 字英文', and '≤240 字英文'. This is a natural-language locale policy constraint that forces a specific language without any indication that the user can choose another language or opt in to English-only output.

Content

No source excerpt is available for this finding.

External Model or Provider Selection

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.

md
一份输入,四份输出,每个平台用各自的原生风格和格式。最高 ROI 的 Skill——
  Blog 每周 4-5 篇,每篇拆解从 20-40 分钟降到 60 秒。技术类内容自动保留"留余地"表述。
  Use when: Blog改社媒 / 一文多发 / 文章拆解 / 多平台内容分发。
model: claude-sonnet-4-6
temperature: 0.65
max_tokens: 1500
triggers:

External Model or Provider Selection

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · skill/SKILL.md (reported line 10)May include surrounding context.

md
一份输入,四份输出,每个平台用各自的原生风格和格式。最高 ROI 的 Skill——
  Blog 每周 4-5 篇,每篇拆解从 20-40 分钟降到 60 秒。技术类内容自动保留"留余地"表述。
  Use when: Blog改社媒 / 一文多发 / 文章拆解 / 多平台内容分发。
model: claude-sonnet-4-6
temperature: 0.65
max_tokens: 1500
triggers:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The listed triggers such as "多平台内容", "blog改写", and the inline "Use when" phrases on L009 are generic enough to match many ordinary writing or marketing requests, not just this specific four-platform blog-to-social workflow. The file does not provide scope limits, exclusion conditions, or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction "全部英文(受众是北美用户)" mandates a specific language for all outputs, and the platform sections also require English, without offering a user choice or opt-in. This is a natural-language policy concern because it hard-codes the output language rather than letting the user select or confirm the locale.

Content

No source excerpt is available for this finding.