Security audit
SwiftButler
Security checks across malware telemetry and agentic risk
Overview
This is a coherent ClawHub/Convex workflow skill set with disclosed, user-directed commands and no artifact-backed hidden or malicious behavior found.
Install only if you want ClawHub maintainer and Convex development workflows that can run local commands, use GitHub or ClawHub authenticated CLIs, publish proof artifacts, and mutate moderation state when directed. For autoreview, use `--no-yolo` or `AUTOREVIEW_YOLO=0` if you do not want the nested review to run in full-access mode.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.