skills/builderio/agent-native/hubspot/Gen Agent Trust Hub

hubspot

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines standard procedures for interacting with HubSpot CRM data through authorized actions and API requests.- [DATA_EXFILTRATION]: The skill processes CRM records like contacts and deals for analysis. It does not attempt to access sensitive local system files, environment variables, or hardcoded credentials.- [PROMPT_INJECTION]: There are no instructions designed to override agent behavior, extract system prompts, or bypass safety constraints.- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads, script executions, or unverified package installations.- [INDIRECT_PROMPT_INJECTION]: While the skill processes data from external CRM sources (emails, notes), there is no evidence of instructions that could lead to unauthorized actions. Ingestion points: HubSpot notes and emails. Capability inventory: Provider API requests. Sanitization: Handled by platform tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:50 AM
Security Audit — agent-trust-hub — hubspot