Security audit
ai-news-collector
Security checks for vulnerabilities and agentic risk
Overview
This is a prompt-only AI news collection skill that asks the agent to search public web sources and summarize results in Chinese.
Install if you are comfortable with the agent making multiple public web searches and fetching pages to prepare AI-news summaries. Be mindful of paywalls, site terms, and the volume of network activity; do not use it to access private or account-only sources unless that is intentional and permitted.
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.