revert.wtf MCP Server Skill
Security checks across malware telemetry and agentic risk
Overview
The artifacts are coherent developer and moderation workflow skills with disclosed, user-directed command use and no evidence of hidden or malicious behavior.
Install only if you want these ClawHub and Convex maintainer workflows available to your agent. Review commands before approving live moderation, GitHub publishing, package installation, remote validation, or full-access autoreview runs, because those actions can affect repositories, PRs, users, or external services.
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.