The Agent Skills Directory

[SAFE]: The skill performs its intended function of codebase visualization without any detected malicious patterns.
[SAFE]: The skill utilizes a well-known rendering service (Mermaid Chart) to process generated diagram syntax. This is an expected and documented part of the workflow.
[SAFE]: A surface for indirect prompt injection exists as the agent processes codebase contents to generate diagrams. However, the impact is mitigated as the resulting data is constrained by Mermaid syntax rules and sent to a specialized rendering tool. 1. Ingestion points: codebase structure via explorer (SKILL.md); 2. Boundary markers: absent; 3. Capability inventory: Mermaid Chart rendering (Step 3); 4. Sanitization: absent.

class-diagram