Back to skill

Security audit

Db Explorer

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent database helper, but it includes high-impact database restore/import/export workflows and unsafe command examples that need careful review before use.

Install only if you are comfortable with an agent receiving database credentials and potentially running export, backup, restore, and migration commands. Use least-privilege or read-only database accounts, avoid putting passwords directly in commands, avoid production Redis KEYS scans, and require explicit confirmation plus target validation before any restore, import, migration, or full export.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:49
Finding

Database Credentials Exposed Through Command-Line Arguments

Content
View full analysis
Remediation
View remediation

other

Warning
Location
SKILL.md:68
Finding

Unbounded Redis KEYS Command Can Disrupt Production Instances

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states it is read-only by default and requires confirmation for writes, but later provides restore/import commands that directly change database state without that promised workflow. This mismatch can cause operators or downstream agents to trust the skill as safe while it still documents ready-to-run destructive commands.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation phrases are broad enough to match common requests like 'check the database' or 'show me the data,' which can cause the skill to trigger in situations where database access was not intended or where a safer skill would suffice. Because this skill can expose data and includes write-capable workflows elsewhere, overbroad activation materially raises the risk of unnecessary sensitive data access or unsafe operations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The export and backup examples write files to disk and later sections include restore operations, but the skill does not clearly warn users about local file creation, sensitive data at rest, or the destructive potential of restores. In practice, this can lead to silent data exfiltration to local files, insecure temporary storage, or accidental restoration into the wrong target.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is presented as a database exploration/query/export tool, but it also includes restore and migration workflows that can modify or overwrite data at scale. In an agent setting, this expands capability from mostly read-oriented inspection to broad write/destructive operations, increasing the chance of accidental or unauthorized data loss.

Content

No source excerpt is available for this finding.