ClawHub
Back to skill

Security audit

claude

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation-only helper for routing Claude API calls through RunAPI, with its credential and network use clearly disclosed.

Install this only if you intend Claude-related prompts and API traffic handled by this skill to be sent to RunAPI using a RunAPI token. Review the broad trigger wording if you want stricter routing for generic Claude help versus RunAPI-specific API usage.

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 skill description is very broad and can match many general requests involving Claude, Anthropic, streaming, multimodal, tool use, token counting, or SDK compatibility. In an agent-routing system, this can cause over-selection of this skill, leading users or downstream agents to send prompts, files, or API traffic to RunAPI when a narrower or more appropriate skill should have handled the request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.