ClawHub
Back to skill

Security audit

调用自定义摘要 API

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it sends text you ask to summarize to an external API, but you should avoid using it with sensitive content.

Install only if you are comfortable sending the text you provide to this external API. Do not use it for passwords, API keys, private documents, customer data, regulated information, or proprietary material unless you trust the endpoint operator and its data-handling practices.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly describes sending user-provided text to an external API but does not provide a clear privacy notice, consent step, or data-handling warning. This is dangerous because users may paste sensitive content assuming local processing, resulting in unintended disclosure to a third-party service.

Ssd 3

Medium
Confidence
96% confidence
Finding
The workflow instructs forwarding all user-provided text to an external API in plain-language terms, which creates a real data-exfiltration risk for sensitive or regulated content. The danger is heightened because the trigger conditions are broad summarization requests, making it likely that users will provide arbitrary private text for processing.

Ssd 3

Medium
Confidence
97% confidence
Finding
The input contract says to use the user's raw original text for external processing, which means the full unmodified content is sent off-platform. That increases the likelihood of leaking secrets, personal information, internal documents, or other sensitive material without any minimization or sanitization step.

External Transmission

Medium
Category
Data Exfiltration
Content
echo ""

# 核心：POST JSON 请求
curl -s -X POST "$API_URL" \
  -H "Content-Type: application/json; charset=UTF-8" \
  -d "{\"content\":\"$USER_TEXT\"}"
Confidence
98% confidence
Finding
The bash script performs a real outbound HTTP POST to a third-party endpoint with user-controlled content, confirming actual external transmission rather than a merely documented possibility. In this skill context, that is more dangerous because the purpose is to process arbitrary user text, so the code operationalizes data exfiltration of whatever the user provides.

Static analysis

No suspicious patterns detected.