fintoio
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/cliglobal package. This is the official command-line utility for the Membrane platform. - [COMMAND_EXECUTION]: The skill utilizes shell commands via the
membraneCLI to perform authentication and execute actions. - [REMOTE_CODE_EXECUTION]: The skill uses
membrane action createto generate new integration logic at runtime on the Membrane platform based on natural language instructions. - [PROMPT_INJECTION]: A metadata discrepancy exists where the skill description refers to a financial aggregation platform 'Finto.io', but the documentation link provided points to 'Finto.fi', a Finnish ontology service. Additionally, the skill has a surface for indirect prompt injection when processing external data.
- Ingestion points: Results from
membrane action runare returned to the agent context. - Boundary markers: No specific delimiters or isolation instructions are provided for external data.
- Capability inventory: The agent can execute platform commands and create new actions.
- Sanitization: No explicit sanitization of external data is defined in the instructions.
Audit Metadata