Back to skill

Security audit

Jarvis Db Query Doctor 01

Security checks for vulnerabilities and agentic risk

Overview

The skill is a generic planning checklist with an overbroad SQL-themed description, but it contains no executable behavior, persistence, credential handling, or hidden data access.

Install only if you want a generic planning and quality-gate checklist. Do not rely on it for SQL performance tuning, safe query rewrites, schema changes, or database-specific safety checks without separate expert review.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill advertises SQL diagnosis and query rewriting, but its body provides only a generic project workflow with no SQL-specific safeguards, analysis steps, or domain constraints. This mismatch can cause an agent or user to rely on the skill for database changes without receiving the promised specialized guidance, increasing the chance of unsafe or incorrect query recommendations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation description is broad enough to match many ordinary development requests, not just SQL performance diagnosis. Over-broad routing increases the likelihood that the wrong skill is invoked, which can displace more appropriate safety- or domain-specific guidance and lead to poor or risky recommendations in unrelated contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The body defines a generic reusable workflow without trigger boundaries, exclusions, or SQL-specific constraints, making the skill applicable far beyond its stated purpose. In an automated skill-selection environment, this ambiguity can cause misapplication and over-trust, especially when users expect specialized database guidance that the content does not actually provide.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.