Security audit
scientific-drawing-skill-1-0-0
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-only scientific drawing skill with disclosed AI-provider keys, local outputs, and optional editor/server behavior, with no hidden executable code in the reviewed artifact.
Install it in an isolated Python environment, review the external AutoFigure-Edit repository before running it, keep API keys scoped, avoid submitting confidential unpublished research unless the chosen provider terms are acceptable, and bind the editor to localhost unless network access is intentional.
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.