gigasheet

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli tool globally via npm, which is a legitimate resource provided by the vendor for this integration.
  • [COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands to perform tasks such as listing actions, managing connections, and sending proxy requests to the Gigasheet API.
  • [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection because it interprets and processes output from external sources. * Ingestion points: Data enters the agent context through the results of membrane action list, membrane action run, and membrane connection list. * Boundary markers: The skill does not define specific markers or instructions to ignore embedded commands in the data retrieved from Gigasheet. * Capability inventory: The skill can execute shell commands via the CLI and perform network operations using the membrane request command. * Sanitization: No evidence of validation or sanitization of external data is present in the skill metadata or instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 09:26 PM