ClawHub
Back to skill

Security audit

AnyGen图表生成-专业版

Security checks for vulnerabilities and agentic risk

Overview

This skill is for a diagram SaaS tool, but its broad trigger and team/API write workflows need review before installation.

Install only if you intend to use AnyGen Pro for diagram generation. Before running it, confirm the exact files, output paths, remote repositories, and team asset targets, and avoid sending confidential architecture or product details to the external API unless your organization permits it.

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 (4)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger condition is broad enough to activate on generic requests involving API integration, webhooks, or system connections, without strong scoping to diagram-generation tasks. In an agent environment with exec/write capabilities, this can cause the skill to engage in contexts where users did not intend file modifications, command execution, or external service usage.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill repeatedly describes exporting files, saving outputs, pushing assets to team repositories, and modifying local/team resources, but does not consistently require explicit user consent before those state-changing actions. This is dangerous because an agent could overwrite local files, create artifacts, or alter shared team assets during normal use without sufficient warning or confirmation.

External Transmission

Medium
Category
Data Exfiltration
Content
--output ./diagrams/user_flow.svg
# ...
# API 集成到文档系统
curl -X POST https://api.anygen.io/v1/diagrams \
  -H "Authorization: Bearer $ANYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
90% confidence
Finding
The skill explicitly instructs sending user-provided diagram descriptions and an authorization bearer token to an external API endpoint. External transmission is expected for a SaaS diagram tool, but it remains security-relevant because sensitive document content or architecture details could be exfiltrated to a third party if users are not clearly warned or if the skill activates too broadly.

External Transmission

Medium
Category
Data Exfiltration
Content
--output ./diagrams/user_flow.svg
# ...
# API 集成到文档系统
curl -X POST https://api.anygen.io/v1/diagrams \
  -H "Authorization: Bearer $ANYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
90% confidence
Finding
The skill explicitly instructs sending user-provided diagram descriptions and an authorization bearer token to an external API endpoint. External transmission is expected for a SaaS diagram tool, but it remains security-relevant because sensitive document content or architecture details could be exfiltrated to a third party if users are not clearly warned or if the skill activates too broadly.

Static analysis

No suspicious patterns detected.