markstream-vue2
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill integrates a component designed to render markdown content from external sources (such as an LLM stream), which constitutes a potential indirect prompt injection surface.
- Ingestion points: The
MarkdownRendercomponent accepts raw markdown via the:contentprop inSKILL.md. - Boundary markers: The skill suggests using "scoped mappings for overrides" to restrict the scope of the integration.
- Capability inventory: The skill facilitates markdown rendering and Mermaid diagram generation within a Vue 2 application.
- Sanitization: The instructions explicitly state to "Keep HTML safe and Mermaid strict" and warn that safe HTML/strict diagrams are necessary to reduce exposure when handling untrusted content.
Audit Metadata