公众号选题 & 爆款标题（AI）
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed WeChat article topic and headline assistant whose file and network access match that purpose.
Install this only in a workspace where the agent may read your .aws-article configuration and product notes and write article draft metadata. If using the full aws-wechat-article suite, review the referenced sibling Python helpers before allowing them to run, because they are outside this skill artifact.
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
64/64 vendors flagged this skill as clean.