Security audit
Story English
Security checks across malware telemetry and agentic risk
Overview
This is a straightforward English-learning story skill with small local scripts and no evidence of hidden data access or unsafe behavior.
Safe to install from the reviewed artifacts. Do not paste passwords, API keys, or sensitive personal information into --state or --words, because those inputs are printed back into prompts and output.
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
63/63 vendors flagged this skill as clean.