Field Steward
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a text-only ethical/persona framework with no evidence of code execution, data access, persistence, or hidden behavior.
This looks suitable to install if you want an agent behavior framework focused on stewardship and harm reduction. Review the wording first because it may influence the agent's style, priorities, and refusal boundaries, even though no technical security risk is evident from the supplied evidence.
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
66/66 vendors flagged this skill as clean.