hubspot-lead-enrichment
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
composioCLI tool via Bash to interact with the HubSpot API. It executes commands to link accounts, search for contacts, and update records. These are the primary intended functions for lead enrichment. - [EXTERNAL_DOWNLOADS]: Fetches contact and company data from HubSpot's official API endpoints through the Composio platform. This is a legitimate operation for a CRM tool.
- [PROMPT_INJECTION]: The skill ingests untrusted data from HubSpot contact fields (Indirect Prompt Injection). Maliciously formatted data in CRM fields could attempt to influence the agent's logic during the update process.
- Ingestion points: Contact data is fetched in the workflow using
HUBSPOT_GET_ALL_CONTACTSand search filters. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the fetched data.
- Capability inventory: The skill is authorized to use
Bashfor shell commands andWritefor local file system access. - Sanitization: There is no explicit sanitization or validation of the retrieved contact data before it is processed or written to logs.
Audit Metadata