ClawHub
Back to skill

Security audit

udi-validator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward UDI validation skill with a local Python CLI, no network behavior, and no persistence or credential handling.

Safe to install for local UDI structure checks. Be aware that --file reads a file path you provide, and the skill performs structural validation only: it does not verify records against official NMPA, FDA GUDID, EUDAMED, HIBCC, or ICCBBA databases.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file states in Chinese that human readers should prioritize README.md, and the overall agent instructions are presented only in Chinese, which effectively imposes a specific language/locale on users or maintainers. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

Line L30 mixes English documentation with the Chinese term "数据库" when referring to the NMPA UDI database. Under the stated policy, forcing or assuming a specific language/locale without opt-in can be a natural-language policy issue, and no user choice or justification is provided here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file presents key operational metadata such as versioning, invocation entry, and related files in Chinese, but does not indicate that the skill is Chinese-only or provide any user language choice. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.