TinkerClaw Model Prompt Adapter
Security checks across malware telemetry and agentic risk
Overview
This skill is a prompt-writing helper with no executable code, network behavior, or hidden data access found.
Before installing, review the suggested prompt snippets because they will influence how your agent behaves in future workspaces. The content is disclosed and security-oriented, but only apply it to instruction files where you want these fallback-model guardrails to persist.
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
58/58 vendors flagged this skill as clean.