Security audit

魔方 Data 轻量版问题解答

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a Data Mini support FAQ, but it publishes fixed login credentials and insecure copyable authentication examples that should be reviewed before use.

Review this skill before installing or sharing it. Remove or replace the fixed default credentials with secure onboarding instructions, rotate any matching deployed account, and update the crypto/auth examples to use environment-specific secrets, stronger algorithms where compatible, and no logging of authentication material.

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 (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:93
Finding: Published Default Login Credentials
Content: View full analysis
Remediation: View remediation
` that cannot function as a real credential. ]]>

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:562
Finding: Weak Hardcoded HMAC Key and Authentication Material Logging
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (5)

Context-Inappropriate Capability

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill discloses a default username and password in plain text, which can directly enable unauthorized access if those credentials are still valid in any deployment. In a FAQ/help skill, this is especially dangerous because it operationalizes access rather than merely describing concepts, making accidental or abusive reuse much more likely.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: Exposing default login credentials without warning normalizes insecure practices and may lead users to attempt shared or unchanged factory credentials in real environments. Because this is customer-facing operational guidance, the context makes it more dangerous: it encourages direct use of credentials in environments that may contain sensitive business or healthcare-related data.
Content: No source excerpt is available for this finding.

Ssd 3

High

Category: Not specified by scanner
Confidence: 100% confidence
Finding: The file plainly discloses and operationalizes a username and password, which is a direct secret exposure issue. Even if intended for setup convenience, publishing credentials in reusable documentation creates a durable compromise path and can result in credential stuffing, unauthorized access, or copy-forward into other environments.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger description includes generic phrases such as “怎么使用XX功能”, “为什么报错XX”, and “如何配置XX”, which overlap with ordinary support questions and could match many unrelated conversations. The file does not provide limiting context, exclusion conditions, or negative examples to clarify when this skill should activate versus when another skill should handle the request.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill goes beyond answering FAQs and provides extensive executable Java/JavaScript workflow scripting examples, including code that manipulates runtime context, mock data, HTTP flows, and cryptographic routines. This expands the skill from informational support into code-generation and operational automation, increasing the chance that users deploy unsafe, overprivileged, or unreviewed scripts into production workflows.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.