unlayer-export
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents functionality that ingests external design data, creating a potential attack surface for indirect prompt injection if the source data is untrusted.
- Ingestion points: External data is loaded into the agent context via
unlayer.loadDesign(saved.design)andunlayer.loadTemplate(templateId)as seen inSKILL.md. - Boundary markers: The provided code snippets do not include explicit delimiters or instructions to ignore embedded content within the design JSON.
- Capability inventory: The skill uses
fetchto interact with both the project's backend (/api/templates) and the official Unlayer Cloud API (api.unlayer.com) to save and export content, as described inSKILL.md. - Sanitization: There is no explicit evidence of data validation or sanitization for the loaded design JSON in the provided instruction snippets.
Audit Metadata