hubspot-bulk-migration

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external CRM exports (Salesforce, Pipedrive, Copper), which presents an indirect prompt injection surface.
  • Ingestion points: Data is ingested from local CSV files (e.g., sf_accounts.csv, sf_contacts.csv) using csv.DictReader in the provided Python examples.
  • Boundary markers: No specific delimiters or 'ignore instructions' markers are used when the agent processes the records for migration.
  • Capability inventory: The skill scripts utilize the requests library to perform bulk writes (create/upsert), associations, and archive operations on the HubSpot API, and use open() to write ID mapping files to the local filesystem.
  • Sanitization: While the skill provides validation against the HubSpot schema for types and formats, it does not implement sanitization to prevent the agent from interpreting instructions embedded in text fields of source records.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:48 AM
Security Audit — agent-trust-hub — hubspot-bulk-migration