Security audit
send21 payment drafts
Security checks for vulnerabilities and agentic risk
Overview
This skill only instructs agents to prepare payment drafts for human wallet review and explicitly forbids handling keys, signing, or broadcasting transactions.
Before installing, understand that the agent may prepare payment draft details such as recipient, asset, network, amount, and memo, but you should only approve funds after checking every wallet output and fee yourself. Do not provide seed phrases, private keys, wallet exports, or signing secrets to the agent or service.
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.