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 thed2command-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
findand 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, andGlobtools. - Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content extracted from the analyzed codebase.
Audit Metadata