The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from npm. This is a standard installation of the official vendor's CLI tool.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI for managing connections, searching for actions, and running automated workflows. These operations are within the expected scope of the tool's integration functionality.
[CREDENTIALS_UNSAFE]: The documentation includes explicit security best practices, advising the agent and user to avoid handling raw API keys or tokens and to use server-side managed connections instead.
[PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection risks. Data ingested from Kintent actions enters the agent's context. While specific boundary markers are not used in the instructions, the recommended use of the --json flag for all commands ensures structured data processing, which mitigates the risk of instructions embedded in external data being executed as commands.

kintent