The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official npm registry. This is a standard procedure for using the vendor's platform tools.
[COMMAND_EXECUTION]: The skill uses the membrane command-line interface to perform operations such as logging in, connecting to services, and running actions. These commands are part of the intended functionality for platform integration.
[DATA_EXPOSURE]: The skill involves processing data from the Circle platform, including member lists, posts, and comments. It utilizes Membrane's server-side connection management to handle OAuth flows, which minimizes the risk of local credential exposure.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from the Circle platform (e.g., post content or member profiles) and possesses the capability to perform write operations (e.g., creating or deleting posts).
Ingestion points: Circle community data retrieved via list-posts, get-member, etc., in SKILL.md.
Boundary markers: None explicitly defined in the prompt templates provided.
Capability inventory: Ability to run actions like create-post, delete-post, and update-member via the membrane action run command.
Sanitization: Relies on the underlying platform and Circle API for data validation.

circle