skills/enitrat/skill-issue/d2-diagram/Gen Agent Trust Hub

d2-diagram

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requirements to generate D2 diagram scripts, creating a surface where instructions could be embedded in the data.
  • Ingestion points: Textual requirements and descriptions provided at runtime (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded within the user data.
  • Capability inventory: The skill generates D2 source code which is intended to be rendered by the d2 CLI.
  • Sanitization: The skill lacks explicit instructions for sanitizing or validating user input.
  • [EXTERNAL_DOWNLOADS]: The skill references verified icon resources from the official Terrastruct library (icons.terrastruct.com) for use in diagrams.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 08:46 AM