Security audit

电商CPS社群文案生成助手

Security checks for vulnerabilities and agentic risk

Overview

The skill does not run code or access private data, but it needs Review because it instructs agents to create fake group-chat customers, purchase confirmations, and urgency for sales.

Review before installing. Use only for transparent promotional copy or clearly labeled role-play examples, and do not use it to impersonate customers, invent testimonials or purchases, or claim scarcity, prices, certifications, returns, or inventory unless those facts are verified.

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 (1)

other

Warning

Location: SKILL.md:95
Finding: Generation of Deceptive Social Proof and Artificial Sales Urgency
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill is entirely described as generating Chinese e-commerce promotional copy and group scripts, with all examples and output requirements written only in Chinese and no indication that the user may choose another language. This creates a locale/language constraint that is not presented as optional or justified as a region-specific compliance requirement.
Content: No source excerpt is available for this finding.

Ssd 4

Medium

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill explicitly instructs the model to generate staged group-chat scripts with '托' accomplices who ask scripted questions, endorse products, post fake purchase confirmations, and create urgency. This facilitates deceptive social proof and manipulative sales pressure, which can mislead consumers into believing there is genuine third-party interest, trust, and scarcity when those signals are fabricated.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.