The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Downloads and installs the @membranehq/cli package from the official NPM registry to manage integration infrastructure. This package belongs to the skill's authoring organization.
[COMMAND_EXECUTION]: Utilizes shell commands to install the CLI, handle authentication, and execute spreadsheet operations such as running SQL queries and managing records.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes data from external Grist spreadsheets which may contain untrusted content.
Ingestion points: External data enters the agent context through actions like list-records and run-sql-query defined in SKILL.md.
Boundary markers: There are no specified delimiters or instructions to prevent the agent from interpreting spreadsheet content as commands.
Capability inventory: The skill possesses command execution capabilities through the membrane CLI and npm as described in SKILL.md.
Sanitization: No sanitization or validation logic is present to filter malicious instructions within the retrieved spreadsheet data.

grist