ClawHub
Back to skill

Security audit

接口测试

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only API testing skill whose permissions and guidance fit its stated QA purpose.

Install only if you want API testing guidance. If using its Bash or WebFetch capabilities, keep requests scoped to systems you own or are authorized to test, and review the separate full skill-set package before installing it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation condition includes a catch-all trigger, “需要测试API时”, which is broad enough to cause the skill to activate in many loosely related contexts. In an agent environment, overly broad routing can lead to inappropriate tool use, excessive scope expansion, or the application of API-testing guidance to requests that were not actually asking for this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.