obsidian-excalidraw-diagram
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a file-writing tool to save diagram data to the local workspace. This behavior is the primary intended function of the skill, enabling the creation of .md and .excalidraw files for diagramming software.
- [PROMPT_INJECTION]: The skill processes user-supplied text to generate diagram content without using explicit delimiters or instructions to ignore embedded commands. This establishes a surface for indirect prompt injection where malicious instructions in the input could potentially influence the output or agent behavior.
- Ingestion points: User-provided text content transformed into JSON (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: File system write access (SKILL.md).
- Sanitization: Performs character replacement for specific punctuation to ensure visual formatting, but lacks sanitization for instructional content.
Audit Metadata