Security audit
worldlines-scenario-authoring
Security checks for vulnerabilities and agentic risk
Overview
This skill gives structured guidance for authoring and testing WorldLines scenarios, with writes scoped to the intended world directory and no hidden install or persistence behavior.
Install this only if you want an agent to help author WorldLines content. Before use, confirm the target world-id is correct because the skill can write scenario files under that world root and may run validators, indexing, MCP health checks, and real-model playtests that use local project context and model/provider access.
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.