wazend
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from WhatsApp messages through webhooks, which presents a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill processes the payload of incoming message events as documented in references/receiving-messages.md and references/webhooks-events.md.
- Boundary markers: The current documentation does not explicitly demonstrate the use of delimiters or specific instructions to the agent to distinguish untrusted message content from internal instructions.
- Capability inventory: The agent is empowered to perform network requests to the Wazend API, including sending messages, configuring webhooks, and managing sessions.
- Sanitization: There is no mention of sanitizing or validating the text content of incoming messages before the agent interacts with it.
Audit Metadata