Security audit
Asking Until 100
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent clarification helper that may slow coding/build work with structured questions, but it does not show hidden access, persistence, exfiltration, or destructive behavior.
Install this if you want the agent to pause and ask structured questions before coding or build changes. Expect extra clarification with strict profiles, and review any repo-local .asking-until-100.yaml because it can tune how aggressively the skill asks questions.
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.
Static analysis
No suspicious patterns detected.