connect-ai-hubspot
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from HubSpot CRM objects which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: HubSpot CRM tables and metadata views (e.g.,
Contacts,Companies,Deals,Engagements,BlogPosts,Comments) queried viaqueryDataacrossHubSpotV3,HubSpotV4, andLegacyschemas. - Boundary markers: No specific delimiters or instructions to ignore embedded content in retrieved HubSpot data are provided.
- Capability inventory: The skill allows the agent to execute SQL queries (
SELECT,INSERT,UPDATE) and sensitive stored procedures includingUploadFile(base64 data handling),DeleteContactPermanently(GDPR erasure), andInsertEngagement. - Sanitization: No data validation or sanitization routines are specified for content retrieved from HubSpot before it is processed by the agent.
Audit Metadata