inbound-lead-qualifier

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWNO_CODEPROMPT_INJECTION
Full Analysis
  • No Executable Code (SAFE): The skill consists entirely of markdown instructions and does not contain any scripts, binary files, or configuration files that execute code.
  • Indirect Prompt Injection (LOW): The skill is designed to process untrusted data from inbound leads (e.g., form fills, demo requests), which creates a surface for indirect prompt injection.
  • Ingestion points: Data enters via form fields such as 'Specific use case mentioned in form' and other lead details.
  • Boundary markers: The instructions lack delimiters or specific formatting to isolate untrusted lead data from system instructions.
  • Capability inventory: The skill influences agent reasoning (scoring/prioritization) and generates content (outreach scripts) but lacks direct command execution or network capabilities.
  • Sanitization: There are no instructions for sanitizing or validating external content before it is processed.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 11:10 PM