Security audit
worldlines-scenario-authoring
Security checks for vulnerabilities and agentic risk
Overview
This is a Markdown-only authoring workflow skill whose file access and edits are scoped to WorldLines scenario work and are mostly protective of user data.
Install only if you want an agent to help author and test WorldLines worlds. Expect it to read local WorldLines project context and player/profile files needed for scenario validation, but its instructions are scoped to the owned world root and tell the agent not to modify engine code, credentials, installed packages, or existing saves without separate authorization.
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