Back to skill

Security audit

Generate Poster

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Flyelep poster-generation API helper that clearly discloses its third-party API call and credential use.

Before installing, users should understand that their generation prompt, any reference image URLs, and their Flyelep API key will be sent to Flyelep. Use a dedicated API key, avoid sensitive product or customer data in prompts or image URLs, and avoid logging full request bodies that contain the secretKey.

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
  • 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
93% confidence
Finding

The skill description and invocation guidance are written as unconditional Chinese instructions, indicating the skill is intended to operate in Chinese without offering any user language choice. The policy requires flagging language or locale constraints when they are forced rather than presented as an opt-in or justified regional requirement.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This skill explicitly instructs the agent to send user-provided content, reference image URLs, and an API secret to a third-party external service. External transmission is expected for this skill's purpose, but it still creates a real data-exfiltration surface because sensitive prompts, image URLs, and credentials are disclosed outside the local environment, and the secretKey is placed in the JSON body where downstream logging may capture it.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

调用示例

生成产品主图(跨境电商,Amazon):

bash
curl -X POST "https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/generate" \
  -H "Content-Type: application/json" \
  --max-time 600 \
  -d '{