Security audit

Db Table Compare

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent database schema comparison purpose, but it documents direct internal database and SSH access with unsafe credential-handling examples that users should review carefully.

Install only if this skill is intended for an authorized internal environment. Before use, replace real infrastructure details with placeholders or approved configuration, use a dedicated read-only schema-inspection account, avoid putting passwords in shell commands, and ensure the agent asks before connecting to databases or SSH hosts.

A.I.G

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 (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:61
Finding: Database Credential Passed Through Shell Command Arguments
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger list includes short generic phrases such as "表结构差异", "生成 alter table", and "字段差异" without clear scope limits or exclusion conditions. In a markdown skill description, these broad phrases can cause unintended invocation when a user is merely discussing database changes rather than requesting this specific skill.
Content: No source excerpt is available for this finding.

Ssd 3

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The example commands instruct direct retrieval of internal MySQL and ODPS table schemas and show concrete hosts, users, and operational access paths. In an agent setting, this can normalize or encourage disclosure of internal metadata and infrastructure details, which may aid reconnaissance even if the workflow is described as read-only.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The skill content, examples, trigger phrases, and outputs are all specified in Chinese, with no indication that the user may choose another language. This can violate a language/locale policy when a skill imposes a specific language without opt-in or documented regional justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.