Security audit
Baserow
Security checks across malware telemetry and agentic risk
Overview
The skill content is coherent and purpose-aligned, with high-impact maintainer actions disclosed and guarded by user-directed workflows.
Use this skill only in repositories and service accounts where ClawHub, GitHub, and Convex maintainer actions are appropriate. Review commands before allowing moderation writes, role changes, PR comments, migrations, package installs, or full-access autoreview, and avoid running it with privileged tokens unless the task requires them.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.