ClawHub
Back to skill

Security audit

Ezer Multi-Agent Report Auditor

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a normal API integration, but it should document its network and environment-variable needs more clearly.

Install only if you are comfortable with the skill running its Python script and making network calls to the configured Ezer API. Prefer a version that documents the exact environment variables, auth token handling, and allowed outbound host in the manifest.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes a Python script that uses environment variables and performs network access, but the manifest does not declare corresponding permissions. This creates a transparency and sandboxing gap: the runtime may grant broader capabilities than reviewers or policy systems expect, and the skill can access internal services via EZER_API_BASE_URL or read sensitive env values without explicit approval.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal