ClawHub
Back to skill

Security audit

Secure Api Toolkit Free

Security checks across malware telemetry and agentic risk

Overview

The skill describes a useful credential-proxy workflow, but its broad activation, persistent API authorization, and mismatched global npm install create review-worthy risk.

Review carefully before installing. Only use this if you intentionally want an external proxy service to see and forward your API requests, and verify the CLI package and publisher before running the global npm install. Prefer a pinned, verified package and revoke provider or machine authorization when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The document claims third-party API credentials are not stored locally, but later instructs users to configure an API key via environment variable. This contradiction can cause operators or agents to handle real secrets locally despite the stated security model, increasing the chance of credential exposure through shell history, process listings, logs, or inherited environment leakage.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill advertises applicability to very broad development activities such as code generation, debugging, testing, and deployment. Overbroad activation criteria can cause the skill to be invoked in unrelated workflows, exposing requests, metadata, or execution capability to a proxy tool when it was not intended, which expands attack surface and raises the chance of unsafe command execution through the included exec tool.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The keyword coverage list is excessively broad, fragmented, and ambiguous, making accidental invocation more likely. In a skill with read/write/exec capabilities and external network-oriented behavior, unintended activation increases the risk of unnecessary command execution, data disclosure to a third-party proxy, or misuse in contexts that did not require this tool.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.