Currents API
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent developer helpers, but the bundled autoreview helper defaults to launching a nested Codex reviewer with full sandbox-bypass authority.
Install only if you trust the publisher and want these ClawHub maintenance workflows. For autoreview, prefer `--no-yolo` or `AUTOREVIEW_YOLO=0`, and be aware fallback reviewers may receive code diffs. Use the moderation and PR tools only with explicit targets because they can make real public or account-level changes.
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
VirusTotal findings are pending for this skill version.