Back to skill

Security audit

MySQL

Security checks for vulnerabilities and agentic risk

Overview

This is a MySQL reference skill made of Markdown guidance, with no executable code, hidden installation behavior, persistence, or credential handling.

Installers should treat this as a database-administration reference: useful, but any generated SQL that mutates schema, terminates sessions, or changes production data should still be reviewed and approved by a human before running against real databases.

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
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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document notes that REPLACE INTO deletes then inserts and may trigger DELETE cascade, but it does not explicitly warn users that this can remove related data or fire destructive side effects. For markdown files, safety-relevant behaviors affecting user data should be clearly called out as warnings, not only described as a technical nuance.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · queries.md (reported line 5)May include surrounding context.

md
## EXPLAIN First

Never ship a query without checking EXPLAIN. Key columns:
- `type`: ALL = full scan (bad), range = index range (ok), ref = index lookup (good), const = single row (best)
- `rows`: estimated rows examined—multiply across joins
- `Extra`: "Using filesort" = sorting without index, "Using temporary" = temp table

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The markdown states that ALTER TABLE commits immediately and cannot be rolled back, but it does not frame this as a user warning about irreversible schema changes. Because this behavior can affect data integrity and recovery expectations, the documentation should explicitly warn users before they rely on rollback safety.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown skill includes KILL <id>, which can terminate running database sessions, but the document provides no explicit user warning about potential disruption to active work. Under the markdown-file criteria for SQP-2, user-facing documentation should disclose behaviors that may affect system integrity or availability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.