Security audit
Teaching Presentation
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent, disclosed workflows for ClawHub/Convex/documentation tasks, including high-impact admin actions that are gated by explicit user confirmation.
Install only if you intend to let the agent assist with ClawHub maintenance, Convex engineering, documentation, or structured review workflows. Pay special attention before using the moderation, email, and migration skills: review the exact command, target, reason, dry-run output, and confirmation prompt before allowing writes or sends.
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.