Cn Construction Mediation
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent and disclose their command use, with sensitive actions tied to explicit review, proof, Convex, or moderation workflows.
Install only in a trusted ClawHub or Convex development environment. Before running moderation, auth setup, proof publishing, or autoreview full-access commands, confirm the target, credentials, and expected external services because these workflows can modify accounts, deployments, repositories, or share diffs with configured reviewer tools.
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
64/64 vendors flagged this skill as clean.