Security audit
Llm Artifacts Detection
Security checks for vulnerabilities and agentic risk
Overview
This is a code-review guidance skill that reads a codebase to flag AI-generated quality issues, with no executable code or hidden data handling.
Before installing, understand that this skill is meant to guide an agent through reading code and producing review findings. It does not appear to execute commands, modify files, collect credentials, or send data externally.
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.