ClawHub
Back to skill

Security audit

表情包回复

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple meme-image lookup helper, but users should know it sends meme search text to an external plain-HTTP service and embeds remote images.

Install only if you are comfortable with meme search queries and image loads going to the documented external HTTP service. Avoid using it in conversations containing secrets, private customer data, or sensitive work context, and prefer a future version that uses HTTPS or a trusted proxy.

SkillSpector

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 (3)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs the agent to send user- or conversation-derived query text to a third-party service over plain HTTP, with no disclosure or consent mechanism. This creates privacy leakage and network security risk because the query contents can expose conversation context, and HTTP allows interception or tampering by attackers on the network path.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill recommends embedding remote images fetched over plain HTTP directly into responses, which exposes users to tracking and content tampering. Because the returned resource is remote and unauthenticated, an attacker controlling the server or network path could swap content, log access metadata, or serve unexpected material.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The default prompt "帮我找个表情包表达我现在的状态" is broad and closely matches ordinary conversational intent, making accidental invocation more likely in normal chat. That can cause the skill to activate without clear user intent, leading to unintended external lookups or responses that change agent behavior.

Static analysis

No suspicious patterns detected.