architecture-visualization
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the agent to install the
d2diagramming tool from well-known sources such asnix shell nixpkgs#d2orgo install oss.terrastruct.com/d2@latestif the command is missing. - [COMMAND_EXECUTION]: The skill uses shell commands to carry out its primary purpose, specifically executing the
d2binary to render diagrams, usingdatefor filename generation, andcommand -vfor tool discovery. - [INDIRECT_PROMPT_INJECTION]: The skill's functionality involves researching the codebase and interpreting its structure, which represents a surface for indirect prompt injection from untrusted source data.
- Ingestion points: Codebase research and dependency identification (SKILL.md, Process Step 1).
- Boundary markers: None identified.
- Capability inventory: Execution of
d2anddatebinaries via shell commands, and file writing capabilities within thedocs/directory tree. - Sanitization: The skill does not explicitly describe any sanitization of codebase data before it is incorporated into visual diagrams.
Audit Metadata