ClawHub
Back to skill

Security audit

coding-2

Security checks across malware telemetry and agentic risk

Overview

The skill fits its dashboard-building purpose, but it asks agents to create database structures, insert data, and call an external API without clear confirmation or scope limits.

Install only if you expect this skill to work with a database and the teamo-dev.floatai.cn API. Before using it, require the agent to show the planned schema, target database/environment, inserted records, and API calls, then get explicit approval before any database creation or data insertion.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill directs the agent to call an external API (`teamo-dev.floatai.cn`) and use database tooling, but the manifest does not declare corresponding permissions or user-visible capability boundaries. This creates a transparency and policy-enforcement gap: an agent may perform networked and state-changing actions that reviewers or runtime controls do not expect.

Tp4

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding
The description frames the skill as dashboard/API development, but the toolkit also includes a local linting/static-analysis script that reads files and reports conventions. Undisclosed file-reading behavior broadens the skill's effective scope and can lead users or orchestration systems to authorize access under a narrower trust assumption than the skill actually requires.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to design database structures, create them, and insert provided data, but it does not require explicit confirmation before performing state-changing operations. In agent environments, silent schema creation or data insertion can damage existing systems, overwrite data models, or create unauthorized records if the user did not intend live modifications.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The skill instructs the agent to design database structures, create them, and insert provided data, but it does not require explicit confirmation before performing state-changing operations. In agent environments, silent schema creation or data insertion can damage existing systems, overwrite data models, or create unauthorized records if the user did not intend live modifications.

Hidden Instructions

High
Category
Prompt Injection
Content
version: 1.0.0
---

<!-- ===== X∞ COMPLIANCE LAYER (auto-applied by skill-architecture-standard) ===== -->
# coding-2 — X∞ Compliance Layer

## 1. IDENTITY
Confidence
87% confidence
Finding
<!-- ===== X∞ COMPLIANCE LAYER (auto-applied by skill-architecture-standard) ===== --> # coding-2 — X∞ Compliance Layer ## 1. IDENTITY Skill milik user: `coding-2`. Mengikuti Skill Architecture Stand

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.