The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package globally via NPM. This is a vendor-provided tool required for the skill's functionality.
[COMMAND_EXECUTION]: The skill relies on shell commands via the membrane CLI for managing ThoughtSpot connections, searching for actions, and executing API requests.
[INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from ThoughtSpot (such as Liveboards, Answers, and Worksheets), which could potentially contain untrusted instructions. 1. Ingestion points: Data is ingested through the membrane action run and membrane request commands. 2. Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between the skill's instructions and the retrieved data. 3. Capability inventory: The skill has the capability to execute shell commands and make network requests via the membrane CLI. 4. Sanitization: No explicit sanitization or validation of the data fetched from ThoughtSpot is defined in the skill instructions.

thoughtspot