skills/diegomarino/claude-toolshed/d2/Gen Agent Trust Hub

d2

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/ensure-deps.sh script provides a help message containing the official D2 installation URL (https://d2lang.com/install.sh). This is an instructional reference for the user and is not executed by the skill.\n- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run internal helper scripts and the D2 CLI for diagram rendering and codebase analysis.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it interpolates user data and code into D2 diagram source files.\n
  • Ingestion points: User-provided diagram descriptions and project files scanned by the architecture tools.\n
  • Boundary markers: Absent; no specific markers are used to separate external data from the skill's logic.\n
  • Capability inventory: The skill is capable of executing shell commands via Bash.\n
  • Sanitization: There is no evidence of sanitization for input data before it is written to D2 files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 09:13 AM
Security Audit — agent-trust-hub — d2