codebase-index
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local codebase (component names, JSDoc, templates) and external sources (Storybook JSON, Figma descriptions) to generate index files.
- Ingestion points: Component source files (SKILL.md Step 2), .ds-ops-config.yml, Storybook URLs, and the Figma API.
- Boundary markers: The skill does not explicitly define delimiters for external content in the generated YAML files.
- Capability inventory: The skill writes machine-readable YAML and Markdown files to the .ai/index/ directory.
- Sanitization: No explicit sanitization or filtering of processed text is mentioned.
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh api) to perform code searches for usage statistics. This is a legitimate integration for analyzing repository activity.
- [EXTERNAL_DOWNLOADS]: The skill fetches component data from external Storybook instances and the Figma API based on user configuration. These operations are standard for design system discovery and management.
Audit Metadata