Security audit
mmxagent-skill-manager
Security checks for vulnerabilities and agentic risk
Overview
This is a simple instruction-only skill that tells the agent to ask before installing or updating a short list of related OpenClaw/IM skills.
Before approving any suggested install or update, verify that the named downstream skill is from a publisher you trust, especially because this skill describes them as official. Do not approve downstream skills that request unexpected credentials, broad filesystem access, or unrelated capabilities.
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.