Wechat Publish
Security checks across malware telemetry and agentic risk
Overview
The skill is a coherent WeChat publishing workflow, but it gives an agent credential-backed authority to upload permanent materials and publish public content without clear approval or rollback boundaries.
Install only if you intend to let the agent operate a WeChat official account. Keep AppID, App Secret, and access tokens out of logs and shell history, review generated content and uploaded images, and require explicit approval before any public publish command is run.
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.