Security audit
walk-the-reality-next-door
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small, coherent guide for connecting to a read-only interactive-fiction MCP server, with no artifact evidence of hidden or harmful behavior.
This appears safe to install if you trust the referenced npm package. The main thing to consider is that the skill connects an MCP client to code fetched through npx, so review or pin the package if you need stronger supply-chain assurance.
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.