Security audit
ia-writing-tests
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only testing guidance skill with no hidden execution, credential handling, persistence, or unrelated authority.
Before installing, note that the skill will steer agents toward writing stronger tests and may recommend real test databases, temp files, containers, or manual cleanup commands for test isolation. Review those recommendations before applying them to important local environments.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.