ClawHub
Back to skill

Security audit

Nationalize

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly scoped to read-only Nationalize lookups, but its setup path tells the agent to execute a downloaded installer script without verification.

Install only if you are comfortable using OOMOL as the connector provider and managing Nationalize access through its account system. Do not let an agent run the installer script automatically; review the official oo CLI installation path and use verification steps where available before installing. After setup, the documented Nationalize actions appear read-only.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install software via a remote script piped directly into a shell (curl ... | bash), which executes unverified code from the network with no integrity check or review step. If the install endpoint, transport path, or hosting account is compromised, this becomes an immediate arbitrary code execution path on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says to use this skill for 'ANY Nationalize request' involving 'searching and reading data', but it does not define the exact trigger scope or exclusions. This broad language can cause unintended invocation whenever Nationalize is mentioned, rather than only for specific supported actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.