Omnisend Automation
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes marketing contact data which could theoretically contain malicious instructions (e.g., in profile fields like
firstNameorlastName). However, this is a standard data ingestion surface for CRM tools and the risk is minimal given the specialized nature of the tools provided. - Ingestion points: Contact data is retrieved via
OMNISEND_LIST_CONTACTSandOMNISEND_GET_CONTACT(SKILL.md). - Boundary markers: No specific delimiters or safety instructions are defined for processing contact profile fields.
- Capability inventory: The skill can perform write operations (create/update contacts, batch operations) via
OMNISEND_CREATE_OR_UPDATE_CONTACTandOMNISEND_CREATE_BATCH. - Sanitization: No explicit sanitization or validation of the ingested contact data is mentioned in the instructions.
Audit Metadata