Security audit

电商爆款主图 Ecommerce Main Image

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly discloses its image-generation workflow, cloud uploads, and saved dLazy login, all of which fit its stated purpose.

Use images and prompts you are comfortable sending to dLazy, protect the saved organization API key, and check credit costs before generating batches. Review product accuracy and platform requirements before publishing results.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (1)

Description-Behavior Mismatch

High

Category: MCP Tool Poisoning
Confidence: 91% confidence
Finding: The only supplied operation is authentication, rather than the advertised image workflow. Authentication could be a supporting implementation detail if tied to a required image service, but the supplied content establishes no such relationship. The command alone does not establish credential theft, data exfiltration, or other malicious behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.