oracle-cloud-hcm

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from npm. This tool is provided by the vendor (membrane) to facilitate interaction with their integration platform.
  • [COMMAND_EXECUTION]: The instructions involve executing various membrane CLI commands, such as login, connection ensure, and action run. These commands are used to authenticate, establish connections to Oracle Cloud HCM, and execute API actions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process workforce and human resources data from Oracle Cloud HCM, which is an external data source.
  • Ingestion points: Data enters the agent context through CLI commands like membrane action run and membrane request (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters for separating data from instructions.
  • Capability inventory: The skill possesses capabilities to read and search HR records, as well as execute actions (write operations) against the HCM environment (SKILL.md).
  • Sanitization: The skill utilizes structured actions and a dedicated proxy to interface with the API, reducing the risk of processing raw malicious payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 09:26 AM