excalidraw-generator
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface as it processes untrusted user input (descriptions, code, or schemas) to generate diagram files. This is inherent to the skill's primary purpose.
- Ingestion points: Processes user descriptions, code snippets, SQL schemas, and configuration files as documented in
SKILL.md(Phase 1). - Boundary markers: No explicit sanitization or delimiters are applied to the input, but the skill enforces strict structural requirements on the generated output.
- Capability inventory: The skill performs file writing operations to create
.excalidrawJSON files and companion.mdfiles. - Sanitization: Implements a robust 10-point validation suite (detailed in
references/validation-checks.md) that independently verifies the JSON structure, element integrity, and semantic completeness before any file is written.
Audit Metadata