search-design-system
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Node.js script
scripts/cli.mjsto perform design system searches and artifact retrieval. It uses a structured command-line interface and parses JSON-based search requests to avoid direct shell interpolation. - [EXTERNAL_DOWNLOADS]: Fetches design system manifests, indexes, and documentation artifacts (such as DESIGN.md) from the author's official GitHub Pages domain (
lintendo.github.io). All downloads are subject to origin validation and mandatory integrity verification via SHA-256 hashing. The fetch mechanism includes size limits and safe redirect handling to prevent resource exhaustion and server-side request forgery. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external documentation content (
DESIGN.md) that could potentially contain instructions aimed at influencing the agent's behavior. - Ingestion points: Content is retrieved from remote URLs or local paths during the fetch workflow.
- Boundary markers: The skill does not explicitly define delimiters when processing retrieved markdown content.
- Capability inventory: The skill has the capability to perform network requests and manage a local object cache, but it does not have the ability to execute arbitrary shell commands from the downloaded content.
- Sanitization: While the skill provides robust validation for the location and integrity of the source files, the textual content of the design documentation is processed without specific prompt-injection filtering.
Audit Metadata