skills/microsoft/vscode/create-skill/Gen Agent Trust Hub

create-skill

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • Instructional Content Only: The skill is composed of natural language instructions to guide the AI in generating a 'SKILL.md' file. It does not include any scripts, executable code, or binary files.
  • No External Communication: There are no network operations, such as 'curl' or 'wget', and no references to external URLs or remote code repositories.
  • Conversation Ingestion: The skill instructs the agent to review conversation history to identify workflows. While this involves processing user-provided data, the output is limited to drafting documentation rather than executing commands or scripts based on that data.
  • Restricted Execution Environment: The skill's metadata includes 'disable-model-invocation: true', which is a platform-level configuration that limits the agent's ability to call other models, providing an additional layer of constraint.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 09:07 AM
Security Audit — agent-trust-hub — create-skill