Core Message Extractor
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only writing skill for distilling drafts into a one-sentence core message, with no evidence of credential use, exfiltration, destructive actions, or unsafe automation.
Install this if you want an agent to read drafts or nearby messaging documents and write a core-message.md summary. Be aware that it may look around the current workspace for related brand or draft files, so use it in a project folder that does not contain unrelated sensitive documents. The crypto and purchase tags in metadata appear inconsistent with the actual skill content.
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.