revert.wtf Agent API Skill
Security checks across malware telemetry and agentic risk
Overview
The skill bundle looks purpose-built for ClawHub maintainers, but it grants high-impact moderation and GitHub workflow authority and includes a review helper that defaults to bypassing sandbox approvals.
Install only if you are a trusted ClawHub maintainer and intend to use staff moderation, PR maintenance, and proof-publishing workflows. Review exact commands before allowing account, role, package, or PR changes, and prefer the autoreview helper's `--no-yolo` mode unless full-access sandbox bypass is explicitly acceptable.
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
59/59 vendors flagged this skill as clean.