Incident Response Lifecycle
Security checks across malware telemetry and agentic risk
Overview
This looks like a repo-specific automation skill set, but it needs review because its autoreview helper defaults to running a nested agent with full sandbox-bypass privileges.
Install only for trusted ClawHub maintainer workflows. Before use, review the autoreview helper and prefer --no-yolo or AUTOREVIEW_YOLO=0 unless you deliberately want nested reviewers to have full local access; keep GitHub, Convex, and ClawHub moderation credentials scoped and confirm any public or account-affecting action before running it.
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
66/66 vendors flagged this skill as clean.