ClawHub
Back to skill

Security audit

Training Certificate Mgmt

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language certificate-management guidance skill with no executable code, network behavior, persistence hooks, or hidden authority.

Before installing, use it in an environment that already has access controls for trainee IDs, verification codes, delivery tracking, and certificate status changes. Confirm revocations, reissues, and public verification details through your normal approval and audit process.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly handles sensitive personal and operational data such as national ID/student ID, delivery tracking numbers, and verification codes, but provides no privacy, minimization, masking, access control, retention, or consent guidance. In a certificate-management context, this omission can lead agents or integrators to collect, expose, or retain more PII than necessary, increasing the risk of privacy violations, unauthorized disclosure, and compliance failures.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill supports state-changing operations such as issuance, revocation, reissuance, and renewal, but does not clearly require authorization checks, approval gates, audit trails, or safeguards against accidental or fraudulent record changes. Because certificate status affects official credential integrity, a weakly constrained workflow could enable unauthorized revocation, duplicate issuance, or inconsistent records that undermine trust in the certification system.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest presents the display name and description entirely in Chinese, which indicates a language-specific user experience. There is no accompanying indication that users can choose their language or that the skill is intentionally limited to a Chinese-language or region-specific context.

Content

No source excerpt is available for this finding.