AI Tech Lead
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only coding workflow that asks an AI agent to research, design, plan, review, test, and commit code with human approval gates.
Install this only where you want an AI agent to participate in structured software development. Review the research, architecture, plans, diffs, tests, and commits before relying on them, and confirm that the skill’s rule against AI co-author tags matches your team’s audit and attribution policy.
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.