orama
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the official Membrane CLI from the NPM registry to facilitate communication with Orama.
- Evidence:
npm install -g @membranehq/cli@latestandnpx @membranehq/cli@latestin SKILL.md. - [COMMAND_EXECUTION]: The skill uses shell commands to interact with the Membrane CLI for authentication, connection management, and executing actions.
- Evidence: Commands such as
membrane login,membrane connection ensure, andmembrane action runare utilized throughout the instructions. - [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for searching and retrieving data from Orama, creating a surface where untrusted data could influence agent behavior.
- Ingestion points: Results retrieved from Orama via
membrane action runandmembrane request(SKILL.md). - Boundary markers: The skill promotes the use of the
--jsonflag across all commands to ensure data is returned in a structured format, which helps delineate data from instructions. - Capability inventory: The skill can execute CLI-based actions, manage credentials server-side, and perform proxied HTTP requests (SKILL.md).
- Sanitization: Instructions emphasize using pre-built Membrane actions which handle pagination and field mapping, reducing the need for raw, unsanitized API interactions.
Audit Metadata