Security audit
Connect agents over A2A
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain troubleshooting guide for connecting two agents over A2A and does not install, execute, or hide any behavior.
Before installing, understand that this skill is guidance for making agents reachable over a network. Use HTTPS, protect bearer tokens, avoid sharing agent-card URLs and tokens broadly, and only expose inbound A2A listeners when you intend another agent to call yours.
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.