Security audit
Clawdex by Koi
Security checks for vulnerabilities and agentic risk
Overview
This skill is a simple security-check helper that asks an external Koi API for ClawHub skill verdicts and does not include executable code or persistence.
Before installing, understand that the skill depends on Koi's external Clawdex service and may disclose the names of skills you check, including installed skill names if you run the audit loop. Treat Clawdex verdicts as helpful security input, not as a complete substitute for reviewing unknown skills yourself.
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.