French
Security checks across malware telemetry and agentic risk
Overview
This skill only gives guidance for writing more natural casual French and does not ask the agent to run code or access data.
This appears safe to install for casual French writing. Be mindful that it encourages informal wording, slang, dropped negatives, and occasional profanity, so it may be inappropriate for formal, professional, or educational contexts unless you explicitly ask the agent for a formal register.
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
58/58 vendors flagged this skill as clean.