ClawHub
Back to skill

Security audit

coding-2

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent dashboard-building helper with disclosed, user-approved API and database actions and no hidden persistence or destructive behavior found.

Install only if you want an agent to help create dashboards that use your own API and database. Before use, confirm the API base URL, session/group ID, database target, collection names, and any write operations; keep credentials in environment variables or explicit config and do not approve unknown third-party endpoints.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill explicitly instructs use of networked APIs and database operations, but it does not declare corresponding permissions. That mismatch can bypass policy expectations and reduce user visibility into what the skill may access, increasing the chance of unintended outbound requests or writes. In this context, the danger is elevated because the skill is designed to connect to APIs, poll periodically, and insert data into a database.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
81% confidence
Finding

The declared description says the skill is for dashboard/API/database work, but the bundled toolkit also performs local file linting and validation behavior not clearly disclosed in the primary purpose. Description-behavior mismatches are dangerous because they can hide side capabilities from reviewers and users, making it harder to assess what the skill will actually do. Here, the hidden behavior is not overtly malicious, but it broadens the operational surface beyond the stated scope.

Content

No source excerpt is available for this finding.