Security audit
ai-news-collector
Security checks for vulnerabilities and agentic risk
Overview
This is an instruction-only AI news collection skill that uses public web research and does not include code execution, credential access, persistence, or hidden installation behavior.
Install this if you want an agent to browse many public news, newsletter, research, and community sources to summarize AI developments in Chinese. Use it in contexts where broad public web browsing is acceptable, and avoid directing it at private intranet pages or sensitive internal sources.
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.