Back to skill

Security audit

SQL Query Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple SQL query optimization helper with no evidence of hidden access, persistence, execution, or data exfiltration.

Review the skill if you need English output or tighter trigger wording, but from a security perspective it only provides static SQL advice and does not ask for sensitive access or make system changes.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description is written as an imperative capability statement in Chinese and the rest of the document continues in Chinese, with no indication that users may choose another language. This creates a natural-language locale constraint without opt-in, which fits the policy category for language or locale violations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger patterns are generic and can activate the skill in broad contexts unrelated to a clearly bounded SQL-optimization task. Overbroad invocation increases the chance the agent will apply this skill unexpectedly, which can cause unsafe or irrelevant handling of user requests and expand the attack surface for prompt or workflow abuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The implementation description and all suggestion strings are written only in Chinese, while the manifest also includes an English trigger phrase. This creates a language-policy concern because users invoking the skill in English are not offered a language choice or told that responses will be Chinese-only.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.