excalidraw-diagram
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted user data to generate diagrams and automatically saves the output as Markdown files using a 'Write' tool, creating a surface for potential injection attacks.
- Ingestion points: User-provided text content used to identify concepts and relationships for diagram generation (defined in SKILL.md workflow).
- Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore malicious instructions embedded within the user's text.
- Capability inventory: The skill requires the ability to write files to the local directory (implementation notes in SKILL.md).
- Sanitization: Absent; while the skill performs character replacement for stylistic formatting (e.g., replacing quotes with brackets), it does not implement security-focused sanitization or validation of the generated filename or content.
Audit Metadata