open-accounting
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing the Membrane CLI (@membranehq/cli) globally via npm. This tool is provided by the service vendor to handle authentication and proxy API requests.
- [COMMAND_EXECUTION]: The skill executes shell commands using the Membrane CLI to manage service connections and perform accounting actions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Open Accounting that could serve as a vector for malicious instructions.
- Ingestion points: Financial data retrieved from the Open Accounting API via Membrane proxy requests.
- Boundary markers: None specified to delimit data from instructions.
- Capability inventory: Shell execution and network access via the Membrane CLI.
- Sanitization: No specific sanitization or validation routines for external data are described in the instructions.
Audit Metadata