d2-architect

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to resolve its installation path and executes a local script (ensure-deps.sh) to prepare the environment. It also relies on the d2 command-line interface for validating and rendering diagram files.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because its core functionality involves reading and analyzing arbitrary user-provided code files (e.g., Python, JavaScript, SQL, Dockerfiles). Maliciously crafted content within these files could attempt to influence the agent's reasoning or behavior during the analysis process.
  • Ingestion points: Source code and configuration files located via find and processed in Step 5.
  • Boundary markers: No specific delimiters or safety instructions are used to distinguish untrusted file content from agent instructions.
  • Capability inventory: The skill has access to Bash, Read, Write, Grep, and Glob tools.
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content extracted from the analyzed codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 09:12 AM
Security Audit — agent-trust-hub — d2-architect