ClawHub
Back to skill

Security audit

API文档生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent API documentation generator with no hidden installer, persistence, or unrelated data-access behavior found.

Safe to install for generating API documentation. Review any generated SDK, curl, mock-server, or test code before running it against real services, especially where real API tokens or create/update/delete endpoints are involved; request a different output language explicitly if needed.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill explicitly forces output language to Chinese regardless of the user's preference. This is not a classic security exploit, but it is a policy/behavioral issue because it overrides user intent and can be used to constrain reviewability or downstream automation in multilingual environments.

Static analysis

No suspicious patterns detected.