Security audit

叉车配件直播运营助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malware, but it needs review because some included sales scripts make unverified safety and commercial claims about forklift parts.

Review and edit the included live-script references before installing or using this skill. Require human approval and product documentation for all safety-critical compatibility, performance, OEM, warranty, price, stock, freight, and promotion claims, and add clear privacy handling rules for customer inquiry records.

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

Findings (4)

other

Warning

Location: references/live-scripts/chain.md:6
Finding: Unverified Compatibility, Performance, Lifespan, and Promotional Claims in Chain Sales Script
Content: View full analysis
Remediation: View remediation

other

Warning

Location: references/live-scripts/fork.md:6
Finding: Unverified Load-Bearing Performance, Compatibility, Warranty, and Pricing Claims in Fork Sales Script
Content: View full analysis
Remediation: View remediation

other

Warning

Location: references/live-scripts/seal.md:6
Finding: Unsupported Diagnostic, Universal Compatibility, Lifespan, and Promotion Claims in Seal Sales Script
Content: View full analysis
Remediation: View remediation

other

Warning

Location: references/live-scripts/tire.md:6
Finding: Unverified OEM Origin, Compatibility, Performance, Pricing, and Warranty Claims in Tire Sales Script
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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases include very broad everyday words such as “复盘”, “总结”, “风险”, “注意”, and “问题”, which can match many unrelated user requests and cause the skill to activate outside its intended forklift-live context. This is primarily an unintended invocation and routing risk rather than a direct exploit, but it can lead to irrelevant handling of user data or unexpected workflow execution.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The form explicitly collects personal and business contact information, including customer name, phone number, location, and company details, but provides no notice about why the data is collected, how it will be stored, who can access it, or how long it will be retained. In a sales/lead-management context with follow-up and transaction records, this increases the risk of privacy violations, unauthorized reuse, accidental disclosure, and noncompliance with data protection requirements.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The invocation rules are defined as broad input categories like '配件名称' or '客户询盘内容' without clear boundaries, making it ambiguous when the skill should take over. In a multi-skill or agent environment, this can cause accidental invocation on generic commerce or customer-service requests that were not meant for this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The entire guide is written in Chinese and does not indicate that language choice is optional or that the content is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.