bland-ai
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the Membrane CLI (
@membranehq/cli) usingnpm. This is the official tool provided by the vendor for managing integrations. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent processes data fetched from the Bland AI API, which creates a potential surface for indirect prompt injection if external data contains malicious instructions.
- Ingestion points: Data enters the agent's context through the output of commands like
membrane action run,membrane action list, andmembrane requestas described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or specific prompt shielding for the ingested API data.
- Capability inventory: The skill includes the ability to perform network requests (
membrane request), execute defined API actions (membrane action run), and manage workspace connections. - Sanitization: There are no documented steps for sanitizing or filtering the content returned from the external API before it is processed by the agent.
Audit Metadata