Opportunity Discovery Engine
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent maintainer/developer workflows with disclosed command, GitHub, Convex, and moderation capabilities, but users should treat them as powerful repo-admin tools.
Install only if you are maintaining ClawHub or a Convex project where these workflows make sense. Review commands before running moderation, PR publishing, Convex deploy/dev, or autoreview helper actions; use dry-run modes and consider disabling autoreview full-access mode with --no-yolo or AUTOREVIEW_YOLO=0 when broad local authority is not needed.
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.
