klaviyo-campaigns
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by processing external user data.
- Ingestion points: The
--profiles-jsonargument inklaviyo_sync_audienceand--propertiesinklaviyo_track_event(found inSKILL.md) allow arbitrary JSON input. - Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands within this data.
- Capability inventory: The skill utilizes the
run_ppc_scripttool to interact with the Klaviyo platform, including creating and sending campaigns. - Sanitization: No evidence of data sanitization or validation is provided in the documentation for the ingested JSON payloads.
Audit Metadata