Security audit
Conservative Code Edits
Security checks across malware telemetry and agentic risk
Overview
This skill only gives conservative code-editing guidance and does not request unusual access, persistence, or hidden behavior.
This appears safe to install if you want agents to make smaller, more cautious code changes. It may cause the agent to ask for confirmation before larger architectural or shared-code edits, which is consistent with its purpose.
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.
Static analysis
No suspicious patterns detected.