Security audit
research-matrix-builder
Security checks across malware telemetry and agentic risk
Overview
The skill set is mostly coherent for ClawHub maintenance, but one review helper defaults to running a nested agent with full unsandboxed local authority, which is more power than a review workflow normally needs.
Install only if you trust this publisher and intend to use repo-maintainer workflows. Before running autoreview, prefer `--no-yolo` or `AUTOREVIEW_YOLO=0` unless full local authority is truly needed, and be aware that fallback reviewers may receive generated diffs. Use moderation and proof-publishing commands only with explicit targets and reviewed commands.
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.
Static analysis
No suspicious patterns detected.