ClawHub
Back to skill

Security audit

ai-newsletter-chn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AI news newsletter generator that uses web search and fetch tools to produce Chinese-language Markdown and JSON summaries.

Install this if you want a daily AI-news digest in Simplified Chinese and are comfortable letting the agent use configured Brave and Firecrawl credentials to search and fetch public web pages. It is not designed for other languages unless edited.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- Truncate to `target_news_count`.
   - Render `markdown_newsletter`.
   - Assemble `json_newsletter`.
   - Apply the language output rule below.
   - Return all outputs.

## Language output
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The description states that the skill produces 'Simplified Chinese output' for a Chinese audience, and the language section later mandates translating the newsletter body and summaries into Simplified Chinese. This is a natural-language locale policy constraint without any indication that the user can choose another language or explicitly opt in.

Natural-Language Policy Violations

Medium
Confidence
99% confidence
Finding
These instructions explicitly require translation of the newsletter body and article summaries into Simplified Chinese while preserving other fields unchanged. Because no user-selectable language option or opt-in is provided, this creates a language/locale policy violation under the stated rules.

Static analysis

No suspicious patterns detected.