hubspot-list-contacts
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Vulnerable to indirect prompt injection from external data. Malicious instructions could be placed within HubSpot contact fields (e.g., first name, email) to influence agent behavior.
- Ingestion points: Data returned from
list_contacts.pyin fields such asemail,firstname,lastname, andcompany. - Boundary markers: Absent. The instruction set does not provide delimiters or 'ignore' instructions for the agent when rendering the contact list.
- Capability inventory: The agent has the capability to execute Python scripts via the shell.
- Sanitization: No sanitization or validation of the fetched contact data is mentioned in the skill definition.
- [COMMAND_EXECUTION] (SAFE): The skill executes local Python scripts located in
00-system/skills/hubspot/. This is the intended mechanism for the skill's functionality and does not involve arbitrary or unsanitized user input in the command line beyond standard pagination cursors.
Audit Metadata