webflow-code-components
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices by explicitly advising users to exclude sensitive credentials (such as Webflow Workspace API tokens) from version control and providing clear guidance on using
.envfiles for local development. - [COMMAND_EXECUTION]: The skill includes a utility script
scripts/search_references.pyused to search the provided documentation. The script implements defensive programming by validating that file paths remain within the skill's root directory and sanitizing the output to strip common prompt injection markers (e.g., 'ignore previous instructions'). - [EXTERNAL_DOWNLOADS]: The documentation describes how to install official Webflow CLI tools (
@webflow/webflow-cli) and common, well-known frontend development packages (e.g., Tailwind CSS, Emotion, Styled Components) from public registries. These are standard dependencies for the skill's stated purpose of React-based Webflow development. - [INDIRECT_PROMPT_INJECTION]: The skill contains logic in
scripts/search_references.pyspecifically designed to mitigate indirect prompt injection risks. It filters documentation content using a regex pattern targeting common override and bypass phrases, ensuring that content retrieved by the agent does not inadvertently contain instructions that could override the agent's behavior.
Audit Metadata