intercom-migration-deep-dive
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing potentially untrusted data from external source systems.
- Ingestion points: Data enters via SourceContact objects and migration arrays in references/implementation.md.
- Boundary markers: No delimiters are present to separate source data from instructions.
- Capability inventory: The skill performs write operations via the Intercom API in references/implementation.md.
- Sanitization: No sanitization is performed.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the intercom-client library, which is the official Node.js SDK for Intercom.
Audit Metadata