Skills
skills/membranedev/application-skills/fatture-in-cloud/Gen Agent Trust Hub

fatture-in-cloud

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing data from the Fatture in Cloud API (e.g., invoices and documents) via the membrane CLI. • Ingestion points: External data enters through the output of membrane action run and membrane request commands. • Boundary markers: None explicitly defined in the instructions. • Capability inventory: The agent can execute further shell commands via the membrane CLI. • Sanitization: No specific sanitization or validation of the API response data is described. This is an inherent property of integration skills and is classified as low risk.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations. All command invocations are limited to the vendor's official toolset.
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs the user to use the vendor's connection management system, which avoids the need to handle or store sensitive API keys locally.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 05:12 AM