memoire-design-tooling
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npxto download and run the@memi-design/clipackage from the NPM registry. This is a standard installation method for the vendor's own command-line tools. - [COMMAND_EXECUTION]: The instructions describe the use of various
memiCLI commands for development tasks, includingmemi agent install,memi scaffold, andmemi research. These commands are used for auditing frontend UI and managing design systems. - [INDIRECT_PROMPT_INJECTION]: The skill includes ingestion points where user-provided strings are passed to CLI commands as arguments (e.g., the
--intentflag). - Ingestion points: Command-line arguments defined in
SKILL.md. - Boundary markers: None present in the command templates.
- Capability inventory: The skill performs file system reads (auditing UI), file writes (scaffolding components), and network operations (registry publishing) via the
memiCLI. - Sanitization: Argument sanitization is handled by the
memiCLI tool rather than the skill instructions.
Audit Metadata