social-writer
Security checks across malware telemetry and agentic risk
Overview
This is a prompt-only social media writing skill with no evidence of hidden actions, credential access, code execution, or persistence.
Safe to install as a writing prompt. Review generated posts before publishing, especially first-person anecdotes, strong opinions, or factual claims, to ensure they are accurate and match your intended public voice.
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
66/66 vendors flagged this skill as clean.