memoire-design-tooling

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute @memi-design/cli@2.7.9 from the NPM registry. This package is a vendor-owned resource used for design audits and component generation.
  • [COMMAND_EXECUTION]: Multiple commands for the memi CLI are documented, enabling the agent to perform interface analysis, scaffold new components, and export design tokens.
  • [PROMPT_INJECTION]: The skill provides an interface for processing user-defined intents.
  • Ingestion points: The --intent parameter in several commands, including memi agent brief and memi research design.
  • Boundary markers: No explicit delimiters are provided in the skill instructions to separate the intent string from other instructions.
  • Capability inventory: The CLI has the capability to write to the file system through scaffolding and export commands.
  • Sanitization: No sanitization or validation logic for the intent input is specified in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 06:58 PM
Security Audit — agent-trust-hub — memoire-design-tooling