Security audit
安全情报雷达
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed security-alert helper that checks vulnerability feeds against a local asset list and keeps local cache/state files.
Before installing, review the feed URL you configure and understand that the skill may read local skill/dependency inventories and keep local cache/state files for deduplication. Its behavior appears purpose-aligned and user-controlled.
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.