Security audit

Db Connector Free

Security checks for vulnerabilities and agentic risk

Overview

This database advice skill is not clearly malicious, but it asks for broad read/write/exec authority and optional database diagnostics that are under-scoped for a mostly knowledge-base skill.

Review carefully before installing. Use it as a database guidance reference only unless you explicitly trust it to run local diagnostics. Do not allow it to print environment variables or credentials, and require confirmation before any command execution or database-changing operation.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:16
Finding: Excessive Tool Permissions for a Knowledge-Only Skill
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description says "Use when 需要数据库操作、SQL查询、数据存储管理时使用," which defines activation in very broad terms rather than with specific trigger phrases or constraints. This could cause the skill to match a wide range of ordinary database-related conversations, with no negative examples or narrower scope beyond a single exclusion about architecture decisions.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest grants read, write, and exec tools even though the skill is presented as a database knowledge assistant. Over-privileged tool access increases the chance that an agent can modify files or run commands unrelated to the user’s intent, especially when the documented role is only advisory.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill claims to be a pure knowledge-base with no extra dependencies, yet elsewhere instructs operational diagnostics such as ping/network checks. This mismatch can cause an agent or user to authorize command execution under the false assumption that the skill is advisory-only, expanding trust beyond what was disclosed.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The error-handling section includes host/network troubleshooting steps like ping and firewall/proxy checks, which are outside the stated scope of a database guidance skill. This broadens the operational surface and may prompt unnecessary command execution on the user’s machine or environment.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The documentation references exec-enabled diagnostics and environment-variable-based credentials without a clear warning about command execution or the handling of sensitive database connection data. In practice, this can lead users or agents to expose secrets, inspect environment variables, or run commands in sensitive environments without informed consent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: Nearly all user-facing documentation, prompts, and examples are presented only in Chinese, and the skill does not state that users may choose another language. Under the policy, a locale or language constraint should either be optional or explicitly justified; here no user choice or justification is provided.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.