Security audit
Joan Workflow
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only workflow guide for Joan that discloses its account, workspace, and file interactions and fits its stated purpose.
Safe to install as a Joan workflow guide. Before using mutation or sync commands, confirm you are logged into the intended Joan account and workspace, review generated CLAUDE.md content, and treat pod pushes, todo updates, archives, and MCP pod retrieval as actions that may affect or reveal shared workspace knowledge.
SkillSpector
By NVIDIA
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
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.