d2lang
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of the
d2CLI tool for formatting, validation, and rendering. These commands are standard operations for the tool and do not involve privileged access or arbitrary code execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate diagram code, creating a standard input surface. It mitigates this risk through an intake gate that explicitly instructs the agent to stop and ask for clarification if a request is ambiguous regarding security, authentication, or data integrity.
Audit Metadata