Security audit

赛博销售

Security checks for vulnerabilities and agentic risk

Overview

This sales-advice skill is coherent and not malicious, but it asks users to provide customer chats, screenshots, and voice content without privacy or consent safeguards.

Install only if you are comfortable using it for Chinese-language sales coaching and can control what customer data is shared. Redact names, phone numbers, account details, pricing, contracts, and other confidential information, and only upload recordings or third-party conversations when you have the right consent or authorization.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description includes very broad trigger phrases such as general customer-reply and sales-advice language, which can cause the skill to activate in many ordinary conversations beyond the user's clear intent. Over-broad activation increases the chance that unrelated or sensitive user content is routed into this skill, creating privacy and prompt-scope risks even without explicit malicious behavior.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill explicitly invites users to paste customer chat screenshots, call transcripts, and messages for analysis but provides no warning about privacy, confidentiality, consent, or data minimization. This is dangerous because such materials commonly contain personal data, business secrets, and third-party communications, and users may disclose them without realizing the legal and security implications.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill instructs users to send raw voice files for transcription and analysis without addressing consent from recorded parties, legal restrictions on recording, or the sensitivity of audio metadata and spoken personal information. Voice content often contains biometric-adjacent and highly identifying information, so requesting raw files without safeguards materially increases privacy and compliance risk.
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 description and installation guidance are entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking region or compliance context. This can violate language/locale policy when a skill imposes a specific language without opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The file mandates a Chinese colloquial register using phrases like '咱', '呢', '哈', '嘛', '呗', and '吧', and frames this as required output behavior. This imposes a language/locale style preference without documenting user choice, opt-in, or a justified region-specific constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file contains all user-facing instructional content in Chinese and does not indicate that the user can choose another language. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.