design-md-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and uses the
@google/design.mdpackage from a well-known organization's official registry. - [COMMAND_EXECUTION]: Instructs the agent to execute shell commands such as
npx @google/design.md lintfor verifying design contracts, which is a core part of its documented workflow. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external
DESIGN.mdfiles, which represents a potential surface for indirect prompt injection. - Ingestion points: Reads front matter and prose from
DESIGN.mdfiles within the workspace. - Boundary markers: No specific delimiters or instructions to ignore embedded prompts are defined for the ingested data.
- Capability inventory: The skill utilizes subprocess execution for linting/diffing and performs file system writes during the creation workflow.
- Sanitization: No explicit sanitization or validation of the ingested markdown content is described.
Audit Metadata