Atelier Litteraire : Redaction litteraire, avec idéation et processus itératif. plusieurs agents : idéation, rédaction, jury/correcteurs.
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed local literary writing workflow with no executable code or hidden data movement found.
Install if you are comfortable using a multi-agent writing workflow that saves project files and memory locally and uses configured Anthropic models. Use a dedicated workspace for sensitive drafts, periodically review generated MEMORY.md/project files, and review final documents before sharing or publishing.
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
65/65 vendors flagged this skill as clean.