Security audit
Cross Agent Notify
Security checks for vulnerabilities and agentic risk
Overview
This skill is a clearly documented coordination protocol for agent handoffs, with no executable code or hidden install behavior found.
Install if you want a standardized multi-agent handoff protocol. Be aware that using it may wake other agents and write shared task/inbox records, so use it in workspaces where that coordination model and Feishu trace channel are expected.
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.