framer-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and code snippets follow standard development practices for Framer plugin integration. No malicious command execution, data exfiltration, or obfuscation patterns were detected.\n- [EXTERNAL_DOWNLOADS]: The provided React code fetches sample data from
jsonplaceholder.typicode.com, which is a well-known service for development testing. This is a standard and safe integration example.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes a data ingestion flow from an external API into the Framer CMS, which presents a surface for indirect prompt injection. However, the risk is minimal given the specialized context of CMS content sync.\n - Ingestion points: External data is fetched via
fetch()fromjsonplaceholder.typicode.cominSKILL.md.\n - Boundary markers: No explicit instructions to the agent to ignore embedded instructions are present in the code snippets.\n
- Capability inventory: The plugin code uses
framer.createManagedCollectionandcollection.setItemsto modify CMS content.\n - Sanitization: The code implements regex-based sanitization (
/[^a-z0-9]+/g) for slug generation.
Audit Metadata