ClawHub
Back to skill

Security audit

Clickhouse Best Practices

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only ClickHouse guidance skill with no hidden execution, persistence, credential access, or exfiltration behavior found.

Installers should treat this as a ClickHouse advice skill: review generated SQL before running it, especially examples involving DROP PARTITION, DELETE, TTL, ALTER, or table migration. Expect responses to lean Chinese unless the host agent or user asks otherwise.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content strongly enforces Chinese-language behavior through the metadata and throughout the instructions, without indicating that the assistant should defer to the user's language preference. This can override higher-level user expectations, reduce usability, and create prompt-control issues where the skill constrains output format unnecessarily, though it does not directly enable code execution or data exfiltration.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · rules/schema-partition-lifecycle.md (reported line 37)May include surrounding context.

-- Instant deletion of old data ALTER TABLE events DROP PARTITION '2023-01';

-- TTL automatically removes expired data

text

**Lifecycle use cases:**

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The markdown recommends '' as an 'empty string' default, and elsewhere uses English semantic labels like 'unknown' and 'never logged in' as normative examples. While mild and likely harmless, the file presents fixed English-language semantics without any opt-in or note that labels may vary by locale, which falls under the policy's language/locale check.

Content

No source excerpt is available for this finding.