ClawHub
Back to skill

Security audit

销售干货日更流水线

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese article-writing workflow that reads and updates a user-chosen local article library, with no evidence of hidden network access, credential use, destructive behavior, or deception.

Before installing, users should choose a narrow article directory and be aware that running the workflow will scan Markdown files there, create new article files, and update the local HTML article library. Users who do not want Chinese-only output or remembered directory preferences should adjust those settings manually or avoid using the skill.

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
  • 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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill declares activation on very broad natural-language phrases such as “写今天的销售文”, “来一篇防骗文”, and especially “日更一篇”, plus automation triggers. These phrases are generic enough that a user could invoke the skill unintentionally in ordinary conversation, causing unexpected file scanning, content generation, and local writes to the article library.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The file contains user-facing documentation and generated content entirely in Chinese, including usage text and the default HTML lang attribute later in the script. Under the policy, forcing a specific language/locale without offering a choice or documenting a justified region-specific constraint is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
98% confidence
Finding
The script creates a default HTML library page with a hardcoded Chinese locale marker and Chinese title text. This enforces a specific locale in produced output without any opt-in mechanism or documented reason, which matches the language/locale policy violation criteria.

Static analysis

No suspicious patterns detected.