ClawHub
Back to skill

Security audit

乌龟图流程技能

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward diagram generator that reads a user-provided JSON file and writes SVG or PNG output files.

Install only if you want an agent to generate local SVG/PNG process diagrams. Keep config and output paths inside your project workspace, and review generated SVGs before sharing if the source text came from an untrusted party.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill instructs reading user-supplied JSON config files and writing generated SVG/PNG outputs, but it does not declare corresponding permissions or constraints. This creates a capability/permission mismatch that can lead to unsafe file access assumptions, weak policy enforcement, and misuse of workspace paths if the runtime relies on declared permissions for isolation.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger conditions include broad natural-language phrases such as '画流程图' and '可视化XX流程', which can cause the skill to activate unintentionally for generic user requests. Over-broad activation increases the chance of the agent invoking file-generating behavior in the wrong context, potentially causing unintended file writes or processing of untrusted input.

Static analysis

No suspicious patterns detected.