Security audit
PayCrow
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small, disclosed payment-trust checker that queries an external PayCrow API before payments and does not include executable code or persistence.
Before installing, understand that the skill may have your agent query PayCrow's external trust API with counterparty wallet addresses and may influence payment decisions based on that service's score. It does not itself send funds, install code, or add persistence; any separate PayCrow MCP escrow setup should be reviewed independently.
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.