Printing Press Library
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent developer and maintainer helpers, but one bundled review helper defaults to running a nested Codex review with full sandbox bypass and broad diff sharing behavior.
Install only if you trust the publisher and want repo-local ClawHub maintainer tooling. Before using autoreview, consider setting `AUTOREVIEW_YOLO=0` or passing `--no-yolo`, and review whether fallback reviewer CLIs may receive sensitive diffs. Use moderation commands only with explicit targets, reasons, and confirmation.
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
65/65 vendors flagged this skill as clean.