klaviyo
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it ingests untrusted data from external Klaviyo resources that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data is retrieved from external sources using tools like
list-campaigns,list-flows,get_profiles_for_list, andget_flow_message(SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or protective headers to separate retrieved data from the agent's system instructions.
- Capability inventory: The agent has extensive write capabilities, including
send_campaign,create_flow, anddelete_data, which are mapped to Hatch-approved CLI commands (manifest.yaml). - Sanitization: The provided files do not describe any sanitization or validation logic applied to the external content before it is processed.
Audit Metadata