disclosure-page-generator
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent workflow helpers with disclosed command use and no evidence of hidden exfiltration, destructive install behavior, or persistence.
Install only if you want these repo-maintainer and Convex workflow helpers. Be careful with moderation and PR-publishing commands because they can affect public ClawHub or GitHub state, and consider disabling the autoreview helper's full-access mode with --no-yolo if you do not want nested review processes to bypass sandbox controls.
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.