ClawHub
Back to skill

Security audit

提供数据库ddl内容,根据自然语言生成sql

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped SQL SELECT generator with a disclosed schema-fetch workflow and no executable code, persistence, or data-changing authority.

Install this only if you are comfortable with the agent using the quoted product name to fetch table-structure metadata over HTTPS from the configured schema endpoint. Do not use sensitive production product identifiers or private schema sources unless that data flow is approved in your environment.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README instructs users to provide a table-schema HTTP API so the skill can obtain database metadata, but it does not warn that schema details may be transmitted to a remote service or exposed over an insecure channel. Database schema information can reveal sensitive internal structure, table names, and business entities, which can aid further attacks or violate data-handling expectations.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 21)May include surrounding context.

text
用户: 使用sql-generator技能
用户: apiUrl=https://api.example.com/tables
用户: requirement=查询所有竞拍中的竞拍信息

小龙虾: [调用技能生成SQL]

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The text says the generated SQL includes Chinese comments, which imposes a specific language behavior. The file does not mention user opt-in, configurability, or a documented region-specific reason for forcing Chinese output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file is entirely written as a Chinese-only skill and explicitly requires '添加中文注释', which imposes a specific language choice on outputs. Under the policy, forcing a language or locale without user opt-in is a natural-language policy violation unless the constraint is clearly justified or optional.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to extract a product name from user input, construct an external URL, and request it to obtain schema information. This creates a data-flow from user input to a network request without any warning, allowlist enforcement, or privacy discussion, which can leak sensitive user-provided identifiers and cause unintended outbound access during skill execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description is written entirely in Chinese and specifies the skill behavior in that locale without any indication that users may choose another language. This can violate language/locale policy expectations when no user opt-in or documented region-specific justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is written entirely in Chinese and specifies behavior such as generating SQL with Chinese comments, which indicates a language constraint. There is no indication that users can choose another language or opt in to this locale-specific behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This manifest description states the skill's capability in broad terms but does not define any specific trigger phrases, activation boundaries, or exclusion conditions. In a manifest file, that ambiguity can make it unclear when the skill should activate versus when ordinary conversation about SQL should not invoke it.

Content

No source excerpt is available for this finding.