Back to skill

Security audit

电商详情页文案生成器

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Chinese e-commerce copywriting helper, but it includes templates for generating credible-looking customer reviews, which can enable deceptive marketplace behavior.

Review this skill carefully before installing. It is technically low risk to your device, but only use it for truthful product-page copy, authentic review summaries, or review-request drafts; do not use it to invent customer reviews, fake usage experiences, unsupported certifications, sales numbers, or artificial scarcity claims.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The markdown explicitly specifies 'Output Language' followed by '中文输出', which imposes a single language choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is documented as justified or optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file title and all instructional content are written exclusively in Chinese, framing the skill as a Chinese copywriting generator without any indication that users may select another language or locale. Under the policy, a skill that imposes a specific language without user opt-in can violate language/locale requirements.

Content

No source excerpt is available for this finding.

Ssd 4

Medium
Category
Not specified by scanner
Confidence
72% confidence
Finding

These lines describe a multi-step sequence that first establishes trust and then culminates in a conversion push, which matches a gradual persuasive narrative pattern. While framed for e-commerce copywriting, the instruction sequence itself is a clear example of incremental influence through staged trust-building and urgency.

Content

No source excerpt is available for this finding.

Ssd 4

Medium
Category
Not specified by scanner
Confidence
75% confidence
Finding

The template lays out a sequential narrative: emotional pain-point framing, value presentation, rational persuasion, immersion, comparison, reassurance, and finally a closing commitment step. Individually benign, the combined progression is a classic gradual-influence pattern that aligns with narrative deception or incremental steering.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This section explicitly provides templates for generating 'seed reviews' and comparative praise, which can enable fabrication of testimonials rather than legitimate product-page copy. In an e-commerce skill, this crosses from persuasion into deceptive content generation and can facilitate review manipulation, consumer fraud, and marketplace policy violations.

Content

No source excerpt is available for this finding.