visual-explainer
Warn
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Dynamic Execution (MEDIUM): The skill dynamically generates HTML files containing JavaScript and automatically triggers their opening in the user's browser. This pattern of runtime code generation and browser execution is a medium-severity vector.
- Indirect Prompt Injection (LOW): The skill ingests untrusted data from local files and git logs without explicit sanitization or boundary markers. This creates an attack surface for XSS if a file in the analyzed repository contains malicious script content. Ingestion: git diff and local files. Boundaries: None. Capability: HTML generation and browser execution. Sanitization: None observed.
- External Downloads (LOW): External libraries (Mermaid, Chart.js, anime.js) are loaded via CDN. These are trusted sources (jsDelivr, Google Fonts), and the usage is consistent with the skill's primary purpose.
- Command Execution (LOW): The skill uses git commands to extract project history and statistics. While necessary for the skill's function, it represents a data exposure surface for the codebase.
Audit Metadata