rb2b-outbound-triggers
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions and templates describe a workflow that ingests untrusted external data (visitor names, titles, and LinkedIn profiles) from the RB2B service for automated processing.
- Ingestion points: The workflow is designed to process external visitor identification payloads received via webhooks as described in
SKILL.md. - Boundary markers: The provided output templates in
SKILL.mdandtemplates/output-template.mddo not implement explicit delimiters or safety instructions to prevent the agent from following directions that might be embedded in the external visitor data. - Capability inventory: The skill describes capabilities for sending Slack notifications, creating CRM records, and enrolling contacts in automated email sequences, creating a potential path for data manipulation if the source data is compromised.
- Sanitization: The instructions do not specify any validation or sanitization steps for the external data before it is interpolated into communication templates or system alerts.
Audit Metadata