Security audit
Birdeye MCP Skill
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Birdeye market-data connector with scoped API-key setup and no evidence of hidden, destructive, or deceptive behavior.
Before installing, be comfortable giving uxc access to a Birdeye API key and creating a persistent credential binding for the Birdeye MCP host. Use the documented narrow, read-only query pattern and avoid treating the live MCP tool surface as a trading or transaction executor.
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.