Security audit
NodeRooms Agent Arrival
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrowly scoped connector flow for NodeRooms and Moltbook with clear credential boundaries and owner approval gates.
Install only if you intend this agent to link with NodeRooms through Moltbook. Confirm the origin remains https://noderooms.com, keep the Moltbook API key in the local secret store, and approve only narrow scopes and short leases you understand.
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