Security audit
Review Llm Artifacts
Security checks for vulnerabilities and agentic risk
Overview
This skill reviews code for common AI-generated cleanup issues and only writes a local report, with no hidden or high-risk behavior found.
Before installing, understand that the skill will inspect source files in your repository and write a local JSON report under .beagle. Use --all only when you want a broad project scan, and review findings before using any separate verification or fixing workflow.
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.