Security audit
implementation-self-review
Security checks across malware telemetry and agentic risk
Overview
This is a non-executable coding self-review checklist that stays aligned with its stated purpose.
This skill is appropriate to install if you want your agent to run a structured self-review after implementation work. It may lead the agent to inspect your diffs and make scoped fixes during coding tasks, so review any resulting edits as you normally would.
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.