webflow-hello-world
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from both the local repository and external documentation, creating an attack surface where malicious content in those sources could influence agent behavior during code generation.
- Ingestion points: Uses
Read,Glob, andGrepon project files andWebFetchfor external documentation. - Capability inventory: Utilizes
WriteandEdittools to create or modify code files. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the fetched documentation or repository files.
- Sanitization: There are no explicit instructions for sanitizing or validating the content retrieved from external URLs before interpolation.
- [EXTERNAL_DOWNLOADS]: Fetches technical documentation and endpoint references from Webflow's official developer portal to guide integration development.
Audit Metadata