Security audit
Pipeworx emojihub
Security checks across malware telemetry and agentic risk
Overview
The skill set is mostly coherent for ClawHub and Convex maintainer work, but it includes high-impact admin workflows and an autoreview helper that defaults to running a nested agent with unrestricted access.
Install only in a trusted ClawHub maintainer environment. Review the autoreview defaults before use, prefer `--no-yolo` when unrestricted nested agent access is not necessary, and avoid fallback reviewers if private diffs must not leave the local environment. Treat moderation commands as production-impacting actions and confirm the exact target and reason before running them.
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.