We Vetted 2000 AI Skills Before They Reached Developers — Lucas Palma, Nubank

Summary

Lucas Palma details how Nubank addressed AI skills—which function like supply chain dependencies—being a significant security risk in a regulated financial environment. To mitigate this, they built 'Skill Vector,' a comprehensive security review system that sits between the skill and the internal marketplace. This system vets every skill using a hybrid approach: deterministic checks (e.g., regex for unsafe instructions) followed by LLM analysis to assess context and behavior before granting permissions or allowing deployment.

Technical details

• Skill Vector Architecture 658s

  Skill Vector is the security review tool implemented to check if an AI skill is safe for use. It operates as a CI step before skills are uploaded to the internal marketplace.

• Vetting Process Flow 737s

  The process involves: 1) Local developer iteration; 2) Pull Request (PR) submission; 3) Deterministic checks (using regex, etc.); 4) LLM review for context; 5) Generating a report in SARIF format; and 6) Final decision/approval gate.

• Security Risks Identified 250s

  Potential risks include hardcoded token requests leading to data leaks, instructions that prompt the use of dangerous shell commands, excessive permissions, and unintentional data exposure.

Mentioned resources

• Skill Vector (Tool/System)
• SARIF (Static Analysis Results Interchange Format) (Format)
• Nubank (Organization)

Channel & topics

• AI Engineer
• AI Security
• Supply Chain Risk Management
• CI/CD
• Software Engineering
• Skill Vector
• SARIF (Static Analysis Results Interchange Format)
• Nubank