broadcast-campaign
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted recipient data by interpolating it into message templates, creating a potential surface for indirect injection.
- Ingestion points: Recipient
templateVariables(e.g.,name,order_id) provided during the contact addition process inSKILL.md. - Boundary markers: The skill uses
{{variable}}delimiters to separate variable data from template text. - Capability inventory: The skill facilitates bulk message transmission across SMS, Email, WhatsApp, and Telegram channels.
- Sanitization: The platform enforces mandatory automated and manual content reviews for non-WhatsApp channels and requires pre-approved templates for WhatsApp to prevent malicious use.
- [DATA_EXFILTRATION]: The skill interacts with the vendor's API at
api.zavu.devto retrieve progress data and manage campaign states. This network activity is limited to the vendor's official domain and is consistent with the skill's primary function.
Audit Metadata