Security audit
Morning Intelligence
Security checks across malware telemetry and agentic risk
Overview
This skill is a self-contained prompt-building interview for a daily news brief, with no executable code or hidden high-impact behavior found.
Review the generated master prompt before putting it into a scheduled task or routine, especially the sources, exclusions, and recency rules. Scheduling it means future runs may gather news from the sources you specify, but the skill itself contains no executable code or automatic persistence.
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.