Security audit
公众号排版 / 小红书封面
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed content-publishing workflow that may send article content and images to GitHub, jsDelivr, WeChat, or the system clipboard only for the features the user chooses.
Install in an isolated virtual environment, prefer the hash-checked requirements file, and only provide GitHub or WeChat credentials when you intend to upload or publish. Use --no-embed-external for private, offline, intranet, or untrusted Markdown because external images are otherwise downloaded for local preview.
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
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep