Security audit
Big AI NEWS from multiple technews sources
Security checks for vulnerabilities and agentic risk
Overview
This is an instruction-only AI news digest skill that fetches public news pages and does not request local files, credentials, installation scripts, or persistence.
Before installing, understand that the skill will make outbound web requests to public AI news sites and may use general web search if source pages fail. It does not appear to access local files, secrets, or accounts; review the default source list if you need different regional or English-language coverage.
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
Static analysis
No suspicious patterns detected.