Security audit
Hybrid Retrieval (BM25 + Vector + Graph)
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-only skill that helps users design hybrid retrieval systems and does not install code, run commands, or access data on its own.
This skill appears safe to install as a retrieval-system design guide. Before using its recommendations on real data, consider whether documents, chats, emails, or agent memory should be sent to external embedding providers or stored in long-lived search indexes.
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.