Security audit
Fairy Team Skills
Security checks for vulnerabilities and agentic risk
Overview
This is an informational skill pack for multi-agent game-development workflows and does not include executable code or request system access.
This appears safe to install as an informational skill. If a future version adds real shared memory, heartbeat automation, background agents, or project file tracking, review where data is stored, who can access it, and how it can be disabled or deleted before using it with sensitive work.
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.