Joan Workflow
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only Joan workflow guide whose account access, workspace changes, and context-file generation are disclosed and aligned with its purpose.
Safe to install as a workflow guide. Before using it, confirm you are logged into the intended Joan account and workspace, review generated CLAUDE.md content, and treat push, update, archive, and MCP pod retrieval as actions that may affect or expose 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.