Signalfx
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts describe repo-specific ClawHub maintenance workflows with clear guardrails and no evidence of hidden or unrelated behavior.
Install this only if you want an agent to help with ClawHub maintainer, moderation, UI proof, review, or Convex development workflows. Before allowing write actions, check the exact command, target, reason, and account permissions because some operations can affect public content, user accounts, PR comments, or audit logs.
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.