glide

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally from npm. This is an official resource provided by the author to facilitate secure communication with the Membrane platform.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to perform actions such as authenticating, listing connections, and running integration tasks. This is the intended method for interacting with the vendor's infrastructure.
  • [PROMPT_INJECTION]: The skill provides capabilities to ingest data from external Glide tables, creating a potential surface for indirect prompt injection. \n
  • Ingestion points: External data is retrieved from Glide via actions like query-single-table and query-tables, or through the membrane request proxy. \n
  • Boundary markers: The skill instructions do not specify the use of clear delimiters or instructions to ignore potential commands embedded within the retrieved table data. \n
  • Capability inventory: The skill has the ability to modify external data using actions like add-single-row, update-single-row, and delete-row. \n
  • Sanitization: There are no explicit sanitization steps defined for the data fetched from the external spreadsheet before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:27 PM