dolthub
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the
@membranehq/clipackage from npm, which is the official command-line interface for the Membrane platform. - [COMMAND_EXECUTION]: Executes shell commands via the
membraneCLI to manage connections, query data, and perform actions on DoltHub. - [DATA_EXFILTRATION]: Ingests and processes data from external DoltHub repositories, creating a surface for indirect prompt injection.
- Ingestion points: Fetches records and API responses via
membrane action runandmembrane request. - Boundary markers: No specific instructions are provided to delineate external data from agent commands.
- Capability inventory: Includes the ability to perform write operations on the database and run CLI commands.
- Sanitization: The skill does not describe specific sanitization or verification steps for data retrieved from external sources.
Audit Metadata