skills/iwanhe/pandawa/code-tour/Gen Agent Trust Hub

code-tour

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions for the AI to follow when generating CodeTour .tour files. It does not contain any scripts, executables, or code that runs on the host system.
  • [DATA_EXFILTRATION]: The skill instructs the agent to read local files to verify paths and line numbers for the tour. This is the intended primary purpose of a documentation tool. There are no patterns suggesting data exfiltration or transmission of codebase content to external servers.
  • [REMOTE_CODE_EXECUTION]: There are no remote code execution patterns. The skill targets the generation of JSON files compatible with the Microsoft CodeTour VS Code extension. The only external link is to the official Microsoft documentation and schema for CodeTour.
  • [PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected. The instructions are clearly scoped to code walkthrough generation.
  • [EXTERNAL_DOWNLOADS]: The skill references the official aka.ms schema for CodeTour validation, which is a trusted service for this domain. No other external resources are fetched.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:32 PM
Security Audit — agent-trust-hub — code-tour