Security audit
BugHerd
Security checks across malware telemetry and agentic risk
Overview
The inspected skills are coherent operational and development helpers with disclosed command use, admin actions, and safety gates.
Install only if you expect these ClawHub/Convex operational workflows. Reviewers should be aware that some commands can send code or diffs to external model providers, and staff/admin actions can mutate production state or send email, but the skill text requires user-directed targets and confirmations before those actions.
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.