instantly-email
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several Node.js scripts to manage campaign lifecycles, lead uploads, and analytics tracking from the command line.
- [DATA_EXFILTRATION]: The skill reads business lead records (including emails, names, and phone numbers) from a PostgreSQL database and transmits them to the Instantly.ai API (https://api.instantly.ai). This involves moving personally identifiable information to an external service, which is the primary intended function of the skill.
- [PROMPT_INJECTION]: The skill handles data from the
business_leadstable, which may contain untrusted content that could influence agent behavior. - Ingestion points: Lead data is retrieved from the database in
scripts/instantly-upload.js,scripts/instantly-add-leads.js, andscripts/push-leads-to-instantly.js. - Boundary markers: There are no specific delimiters or instructions present to prevent the agent from obeying instructions embedded within the lead data.
- Capability inventory: The skill is capable of performing database updates and making external network requests to a third-party API.
- Sanitization: The scripts do not perform explicit sanitization or validation of the lead data retrieved from the database before processing or uploading it.
Audit Metadata