paid-marketing-lead-enrichment-bdr-list-skill

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local system commands and scripts to perform its tasks. It uses bash to dynamically compute dates for scheduling and executes a Python script (recalc.py) to process and format XLSX workbooks.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface.
  • Ingestion points: Data is pulled from HubSpot hubspot_contacts (Step 1, Step 2), including user-controlled fields like names, job titles, and company names.
  • Boundary markers: The instructions do not specify the use of delimiters or "ignore" instructions when processing these fields.
  • Capability inventory: The skill can execute SQL queries, run bash/python commands, write to the file system, and interact with external enrichment APIs.
  • Sanitization: There is no mention of sanitizing or escaping the contact data before it is interpolated into tool inputs or generated HTML/XLSX reports.
  • [DYNAMIC_EXECUTION]: The instructions require the agent to use execute_sql via an MCP to perform searches and groupings on CRM data. This involves the dynamic generation of database queries based on contact attributes fetched during the pipeline execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:54 PM