Security audit
忘情水会问版（禅意情感治愈类）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a documentation-style wrapper for a local narrative engine and does not show hidden data access, network transfer, or destructive behavior.
Install only if you intend to use the Mengpo narrative engine workflow. Before running the optional self-test, review the copied selftest.js and run it in the intended engine project because it loads local project modules for validation.
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.