beautiful-mermaid

Warn

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs the installation and use of the beautiful-mermaid package from the NPM registry and GitHub repository lukilabs/beautiful-mermaid. As lukilabs is not a listed trusted organization and is unaffiliated with the skill author 'ThinkfleetAI', it is considered an unverifiable external dependency.
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided Mermaid code blocks, creating a risk of indirect prompt injection.
  • Ingestion points: User-supplied Mermaid code blocks (mermaid ... ) analyzed in SKILL.md.
  • Boundary markers: Absent. The skill does not provide instructions to the agent to ignore or delimit potentially malicious instructions embedded within the diagram syntax.
  • Capability inventory: Uses renderMermaid to generate SVG output and renderMermaidAscii for text output, which may be rendered in sensitive UI contexts.
  • Sanitization: None mentioned. The skill does not describe any validation or escaping of the input Mermaid text or the resulting SVG output to prevent potential injection or cross-site scripting (XSS) vectors.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:13 AM