Security audit

育儿早教助手

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly transparent about paid parenting advice, but its payment workflow has review-worthy problems including an unrelated payment intent label and an unpinned external installer.

Review before installing. Only use this if you are comfortable sending parenting prompts to the disclosed remote service and paying through Alipay. Avoid running the unpinned @latest installer unless you can verify the package version and publisher, and treat the unrelated payment description as a reason to confirm charges carefully before approving payment.

A.I.G

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

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection

Findings (15)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.
md
### 调用流程（scripts/paid-call.mjs）

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.
md
### 调用流程（scripts/paid-call.mjs）

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 105)May include surrounding context.
md
### 调用流程（scripts/paid-call.mjs）

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.
md
### 调用流程（scripts/paid-call.mjs）

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.
md
### 调用流程（scripts/paid-call.mjs）

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The file's behavior is a paid remote invocation and payment orchestration flow, not parenting or early-education assistance logic. This mismatch is dangerous because it obscures the true capabilities of the skill, making trust decisions harder and increasing the risk that users authorize networked payment operations they did not expect from the declared skill purpose.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill is presented entirely in Chinese, beginning with the display name and continuing through the instructions, with no indication that users may choose another language. Under the policy, forcing a specific language without opt-in or a clearly justified region-specific limitation is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list contains broad everyday parenting phrases such as 育儿, 早教, 几岁会, and 亲子游戏, which can match normal conversation too aggressively and cause unintended invocation. In practice this can route unrelated or sensitive family discussions into a paid external workflow, increasing privacy and billing risk.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 95% confidence
Finding: The skill instructs users to run npx -y @alipay/agent-payment@latest install, which fetches and executes the latest package version at install time. This creates a supply-chain risk: if the package is compromised or a breaking/malicious version is published, users may execute unreviewed code on their systems.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This code file contains natural-language documentation and runtime messages entirely in Chinese, including required usage guidance and error/help text. That effectively imposes a specific language on users without any opt-in or alternative, which matches the locale-policy violation criteria.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 87% confidence
Finding: The script instructs users to install and run '@alipay/agent-payment@latest' via npx without pinning a specific version. This creates a supply-chain risk: a compromised or malicious future package release could be fetched and executed automatically on the user's machine with the script's trust context.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The script launches external programs ('curl' and 'alipay-bot') even though such behavior is not justified by the stated parenting-assistant functionality. Spawning subprocesses broadens the attack surface through PATH hijacking, unsafe environment inheritance, and hidden network/payment side effects that users would not reasonably expect in this context.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The payment intent summary references '种草图文笔记创作', which is unrelated to parenting or early education. This inconsistency is a strong indicator of copied or repurposed payment code and can mislead users during authorization, increasing the risk of deceptive consent or mis-billing.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 84% confidence
Finding: The runtime error message again directs users to execute an unpinned '@latest' package install command. Repeating this guidance increases the chance that users will fetch whatever version is currently published, exposing them to remote code execution through package compromise or typosquatting-like publisher takeover scenarios.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.