Security audit
4Aachitecher
Security checks for vulnerabilities and agentic risk
Overview
This is an instruction-only architecture-diagramming skill that asks for product context and may validate claims against public sources, with no executable code or hidden data handling found.
Before installing, consider that the skill may lead your agent to browse public authoritative sources and may process product or architecture details you provide. Avoid pasting confidential internal architecture information unless you are comfortable using it in prompts, and review generated draw.io XML before importing it into sensitive environments.
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.