Security audit
Report-to-Content Factory / 研报内容创作工厂
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed workflow for turning authorized research into drafted content and saving related records, with no automatic publishing or hidden execution found.
Before installing, confirm you are comfortable granting the agent write access to the selected JishuDB knowledge base and allowing it to archive permitted research material, drafts, citations, and revision records. Use it only with public or authorized sources and avoid supplying confidential documents unless the chosen KB and retention rules are appropriate.
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
Static analysis
No suspicious patterns detected.