Security audit

db-free

Security checks for vulnerabilities and agentic risk

Overview

This database guidance skill is mostly documentation, but it asks for broad command, read, and write authority that is not well scoped to its advisory purpose.

Review this skill before installing because it requests broad local execution and file authorities while mainly providing database advice. It should be safer if limited to read-only guidance or tightly scoped, user-confirmed database diagnostics; avoid entering secrets or allowing automatic command execution unless you have verified the exact commands.

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

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill is presented as a database pitfall guidance tool, but later advertises broad automation capabilities including file handling, API calls, and system command execution. This scope expansion can cause an agent or user to grant or invoke powerful behaviors not required for the stated purpose, increasing the attack surface and enabling misuse through over-privileged execution paths.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The summary and description say to use the skill whenever database operations, SQL queries, or data storage management are involved, which covers a very large range of ordinary development activity. Although it excludes architecture decisions, it does not provide specific trigger phrases, scope boundaries, or negative examples to prevent unintended invocation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file repeatedly states that the skill provides Chinese interaction and supports Chinese interaction, but it does not indicate that language is optional or user-selectable. That can violate language/locale policy expectations when users have not opted into Chinese output.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill introduces external API usage and API key configuration even though its stated purpose is advisory guidance on database pitfalls. This can normalize unnecessary secret handling and external communication, creating opportunities for credential exposure or unneeded network access in contexts where neither should be required.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The deadlock entry correctly identifies a database concurrency problem, but the remediation diverts users toward ping, firewall, and proxy troubleshooting that is unrelated to deadlock resolution. In an automated or semi-automated context, this can waste time, trigger unnecessary network actions, and obscure the real transactional cause, delaying recovery and potentially worsening availability incidents.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The document states that schema change safety strategy and scalability planning are paid-only features, yet immediately gives operational recommendations for safe schema modification and handling tables over 100 million rows. This is not merely incomplete documentation; it actively undermines the stated boundary of what the free version includes.
Content: No source excerpt is available for this finding.