Firestore
Security checks across malware telemetry and agentic risk
Overview
The reviewed artifacts appear to be disclosed, repo-focused developer instructions with no evidence of hidden exfiltration, destructive automation, or deceptive behavior.
Install or use this only in the intended ClawHub developer or maintainer context. Review commands before running workflows that touch moderation, GitHub, Convex deployments, package installs, or nested review tools, because those can affect local files or live services when supplied with valid credentials.
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.