Security audit
iaiops-sensor
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed industrial sensor-reading workflow with mostly read-only tools and clear safeguards around its one MQTT write capability.
Install only in environments where the iaiops sensor tooling is expected to access Modbus, IO-Link, serial, or MQTT sensor infrastructure. Treat `mqtt_publish` as a separate write-capable operation and keep its approval gate enabled; for normal sensor onboarding, prefer the documented read-only path and human-reviewed config changes.
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.