html-flowchart-anthropic
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected.
- [COMMAND_EXECUTION]: The provided scripts (
src/build.ts) perform standard filesystem operations to create directories and write generated HTML and SVG files. These operations are limited to local project paths and do not involve executing arbitrary shell commands or processing untrusted external input. - [DATA_EXFILTRATION]: There are no network operations, such as
fetch,curl, orwget, present in the code. The skill does not access sensitive system directories (e.g.,.ssh,.aws) or environment variables. - [PROMPT_INJECTION]: The instructions in
SKILL.mdare strictly focused on design tokens, typography, and layout logic. While the term "injection" appears in the documentation, it is used contextually as a label for a node in a demonstration flowchart (e.g., "System prompt injection") and does not constitute an attempt to override the AI's safety guidelines or instructions. - [DYNAMIC_EXECUTION]: The build system generates static HTML files based on predefined TypeScript specifications. It does not use
eval(),exec(), or other dynamic execution sinks to process external or generated code at runtime.
Audit Metadata