disqualification-handling

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted lead data (such as names and company descriptions) and interpolates them into email templates for drafting.
  • Ingestion points: Receives 'disqualified-leads' data from the upstream 'inbound-lead-qualification' skill.
  • Boundary markers: None explicitly defined; data is inserted directly into placeholder fields within the templates.
  • Capability inventory: Includes email drafting, CRM updates (HubSpot, Smartlead, etc.), and file system read/write access.
  • Sanitization: No explicit sanitization or filtering of lead-provided strings is described in the instructions.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses and stores lead information locally in CSV files and configuration JSONs within the 'clients/' directory. It also transmits this data to authorized external CRM platforms as part of its core functionality. These operations are transparent and consistent with the skill's stated purpose.
  • [COMMAND_EXECUTION]: The skill utilizes external tools like Supabase and various CRM APIs. These tools are used for standard data persistence and lead management operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — disqualification-handling