lead-routing
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from multiple external channels.
- Ingestion points: Lead details are captured from webinar registrations, ad forms, and content downloads as specified in the Inputs section of SKILL.md.
- Boundary markers: No explicit delimiters or instructions are provided to distinguish between lead data and agent instructions.
- Capability inventory: The skill triggers Slack notifications, sends automated emails via templates, and modifies CRM records.
- Sanitization: There is no evidence of sanitization or validation of lead data before it is interpolated into communication templates.
- [NO_CODE]: The skill consists entirely of instructional Markdown content and does not include any executable script files or binary dependencies.
Audit Metadata