oracle-fusion-recruiting-cloud
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with and process data from Oracle Fusion Recruiting Cloud, including candidate profiles, job applications, and talent community memberships. This data is externally sourced and can contain untrusted content.
- Ingestion points: Data retrieved from Oracle Fusion Recruiting Cloud endpoints via
membrane action runormembrane request(e.g., job applications, candidate details, talent community member data) inSKILL.md. - Boundary markers: The instructions do not define delimiters or specific system prompts to isolate external data from the agent's core instructions.
- Capability inventory: The skill provides capabilities to execute actions (
membrane action run) and perform arbitrary API requests (membrane request), which could be leveraged if the agent is manipulated by injected content. - Sanitization: No explicit sanitization or filtering of the retrieved recruiting data is performed before it is presented to the agent.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the Membrane CLI (
@membranehq/cli) from the official NPM registry to manage authentication and tool execution. - [COMMAND_EXECUTION]: The skill utilizes the Membrane CLI and standard Node.js package managers (
npm,npx) to perform operations such as logging in, creating connections, and executing API actions.
Audit Metadata