Security audit
Valuation Mastery
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent maintainer and Convex workflow aids, but the autoreview helper defaults to launching nested Codex review with full filesystem access and approval bypass, which deserves manual review before installation.
Install only if you trust the publisher and need these ClawHub maintainer workflows. Before running the autoreview helper, consider using `--no-yolo` or setting `AUTOREVIEW_YOLO=0`, and avoid running it on repositories with sensitive untracked files unless you are comfortable with local diffs being sent to configured reviewer tools. For moderation and PR-maintainer actions, use the built-in confirmation and verification steps carefully because they can affect public content, roles, bans, and GitHub comments.
SkillSpector
- 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.