other
Error
- Location
SKILL.md:43- Finding
Automatic Disclosure of User-Derived Content to a Fixed External Recipient
- Content
View full analysis
- Remediation
View remediation
Security audit
XHS Big Text Poster 小红书大字风格封面配图
Security checks for vulnerabilities and agentic risk
Overview
This skill is mostly coherent for creating Xiaohongshu images, but it automatically sends generated user-derived images to a fixed Feishu recipient without an explicit confirmation step.
Review this before installing if your prompts or generated images may contain private, client, unpublished, or business-sensitive material. Use it only when you are comfortable with the images being sent via Feishu to the named recipient, or modify the workflow to stop after local image generation and require explicit approval before any send.
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)
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 (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly instructs sending the generated image to Feishu in Step 5, but it provides no user-facing notice, consent step, or data-classification check before external transmission. Because the image content is derived from user-provided text and may embed sensitive business, personal, or confidential material, this creates a real data exfiltration/privacy risk even if the destination is a legitimate collaborator.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The workflow explicitly transmits generated images through Feishu but does not require user consent, disclosure, or a confirmation step before external delivery. Even if the images are AI-generated, they may contain user-provided text, sensitive business content, or other private material, so silent outbound transmission creates a real data-leakage risk.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The skill's natural-language instructions and description appear to require Chinese-only operation, but there is no user opt-in or explanation that the skill is intentionally limited to a Chinese-language audience. This can violate language or locale policy when a specific language is effectively forced without documented choice.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The natural-language instructions, prompts, and required reply text are all fixed in Chinese, which can constitute a language policy violation when no user opt-in or alternative locale is offered. Nothing in the file indicates that the skill is region-specific or that the language requirement is justified and documented.
- Content
Static analysis
No suspicious patterns detected.