ClawHub
Back to skill

Security audit

TiDB Cloud Zero

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only helper for creating and using a temporary TiDB database, with one optional API-key handling caveat users should treat carefully.

Before using optional BYOK embedding examples, treat OpenAI, Cohere, or other provider keys as sensitive secrets. Use test-scoped or short-lived keys where possible, avoid shared databases for long-lived credentials, and rotate keys if they were pasted into a disposable or untrusted database session.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation shows users setting provider API keys directly through SQL global variables without any warning about secret handling, storage, access controls, or log exposure. In a disposable/shared cloud database context, this can lead users to paste long-lived credentials into an environment where they may be visible to administrators, exposed via query history, or reused unsafely across sessions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.