ClawHub
Back to skill

Security audit

朋友圈文案生成器

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward WeChat marketing-copy generator that uses DeepSeek, with privacy and API-key considerations users should understand.

Install only if you are comfortable using DeepSeek for generation. Do not enter confidential customer data, unreleased campaign plans, or sensitive business information unless you are comfortable sending it to DeepSeek, and use an API key with appropriate billing limits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill’s trigger example is a very generic natural-language request ('帮我写一条 [产品类型] 的朋友圈文案，风格 ...'), which can easily overlap with ordinary user conversation and unintentionally activate the skill. Overly broad invocation patterns increase the risk of prompt hijacking, unintended routing, or accidental execution in contexts where the user did not mean to call this skill.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description states a broad capability to generate marketing copy with one click, but it does not define when the skill should activate, what user consent is required, or what limits apply to promotional content. Overly broad metadata can cause the agent to invoke the skill in unintended contexts, increasing the chance of spammy, manipulative, or policy-violating content generation.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The skill metadata is entirely Chinese-language and presents Chinese output behavior without stating that this is optional or user-selected. This can cause the agent to route users into a language-specific skill without clear opt-in, creating usability issues and increasing the risk of mismatched output or unintended persuasion content in the wrong language context.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script sends user-supplied product text to an external third-party API and includes an API credential in the request, but provides no disclosure, consent, or indication that data will leave the local environment. This can expose sensitive business information or personal data if users assume the tool operates locally, and the risk is heightened because the key is also sourced from a local config file without explicit user awareness.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.