Security audit
Delivery Mirror
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent with their stated development, documentation, Convex, review, and ClawHub staff-workflow purposes, with no evidence of hidden or malicious behavior.
Install only if you want these operator-oriented workflows available to your agent. Before using the ClawHub moderation, content-rights, migration, or PR-maintainer skills, verify you are in the intended repository and account, read the command preview, and only approve writes, sends, production deploys, or cleanup steps after confirming the exact target and impact.
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
63/63 vendors flagged this skill as clean.