do-bootstrap-design-system
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands including
git rev-parseto identify the project root, git branching commands to follow project policies, andcurlcombined withgrepto verify the generated style-guide page on the local development server. These operations are standard for development automation and performed within the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill ingests various project files (CSS, Markdown, TypeScript, configuration files) to discover design tokens and brand rules. While these files are external to the skill itself, the risk of malicious instructions being processed is low as they are used to populate a structured 9-section design specification. The skill provides clear formatting boundaries (tables, specific sections) which help maintain the integrity of the generated output.
- [SAFE]: No external network exfiltration, remote code execution from untrusted sources, or persistence mechanisms were detected. The skill's behavior aligns with its stated purpose of improving project documentation and design consistency.
Audit Metadata