Security audit
agent-throne
Security checks for vulnerabilities and agentic risk
Overview
The skill is clear about its crypto-payment purpose, but it asks users to run unpinned remote code and handle wallet keys and irreversible USDC transfers.
Install only if you are comfortable with an agent workflow that can publish public content and initiate irreversible USDC payment authorization steps. Do not run the quickstart or fund any generated wallet until you have reviewed the downloaded script, verified the treasury and amount, and enforced your own signer-side spend cap; the skill and server state that they do not enforce that cap for you.
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.