inbound-lead-enrichment
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes 'raw-lead-data' sourced from external inbound leads, creating a potential surface for indirect prompt injection attacks where malicious data could influence agent behavior.
- Ingestion points: The skill accepts untrusted data including emails, names, and company info from inbound leads as defined in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or warnings to treat the lead data as purely informational, which may lead the agent to interpret instructions embedded in data fields.
- Capability inventory: The skill possesses broad capabilities including
web-search,linkedin-scraping,crm-lookup, and write access to external CRMs and databases (Supabase, HubSpot, Salesforce). - Sanitization: No specific sanitization or validation steps are documented for the external data before it is used in automated research tasks or system updates.
Audit Metadata