skills/jeremylongshore/tons-of-skills-marketplace/webflow-reference-architecture/Gen Agent Trust Hub
webflow-reference-architecture
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 and analyze potentially untrusted data from the local repository and external Webflow documentation.
- Ingestion points: The agent uses Read, Glob, and Grep to inspect project files and WebFetch to retrieve content from external URLs (developers.webflow.com).
- Boundary markers: The instructions lack specific guidance for using delimiters or boundary markers to differentiate between architectural instructions and content within the analyzed files.
- Capability inventory: The skill allows the agent to use Write and Edit tools to modify the repository based on the information gathered during analysis.
- Sanitization: There are no instructions provided for sanitizing or escaping content retrieved from the repository or external documentation before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill retrieves current official reference material from Webflow's developer documentation portal (developers.webflow.com), a well-known service.
Audit Metadata