Security audit
Falsifiability
Security checks across malware telemetry and agentic risk
Overview
This is a text-only reasoning skill for making claims testable, with no evidence of hidden code, data access, persistence, or unsafe behavior.
This appears safe to install as a reasoning helper. It may influence the agent to challenge vague empirical claims and ask for testable thresholds, so users should expect more structured questioning when discussing strategies, experiments, or investment theses.
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.