Moin
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only tweet-writing skill that uses web research for examples and does not request account access, code execution, persistence, or credentials.
Safe to install for drafting tweets and threads. Avoid putting confidential launch plans, customer names, private strategy, or unreleased product details into prompts that the skill may turn into web search queries.
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.