platform-engineer
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only platform engineering guidance skill with no executable code or credential collection, though it should be used carefully around real infrastructure changes.
Install is reasonable for platform-engineering assistance. Before allowing an agent to act on this skill, scope credentials and tool access tightly, require human approval for production deployments, access-control changes, GitOps repository changes, resource scaling, and multi-cluster updates, and ask the agent to substantiate any claimed metrics or completion statements with actual 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
64/64 vendors flagged this skill as clean.