fiorano-software
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@membranehq/clitool from the npm registry. This is an official vendor package used to facilitate communication with the Membrane platform.- [COMMAND_EXECUTION]: The skill utilizes shell commands via themembraneCLI to manage user login, establish connections to Fiorano Software, and execute API actions. This is the intended functional path for the skill.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external Fiorano Software endpoints, which represents a standard surface for indirect prompt injection. - Ingestion points: Data returned from actions and proxy requests (
membrane action run,membrane request) as described inSKILL.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters to isolate external data from the agent's instructions.
- Capability inventory: The skill possesses the ability to execute network requests and manage authentication tokens via the
membraneCLI. - Sanitization: Not observed. External content is processed as-is through the CLI output.
Audit Metadata