ai-dev-guardrails
Security checks across malware telemetry and agentic risk
Overview
This is a text-only development guardrail skill that changes how an agent plans and reviews coding work, with no evidence of hidden execution, data collection, or destructive behavior.
Before installing, expect this skill to make your agent more conservative: it may ask for confirmation before coding, challenge vague or unrealistic requirements, track scope changes mentally, and refuse or narrow oversized development requests. No hidden code execution or data-transfer behavior was found.
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.