The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @membranehq/cli package from the NPM registry and recommends using npx to discover actions. These resources are part of the vendor's official ecosystem on a well-known registry.
[COMMAND_EXECUTION]: The instructions guide the agent to perform shell commands using the membrane CLI for authentication, connection management, and running actions. These operations are required for the primary functionality of the skill.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it is designed to retrieve and process news articles from the web. Maliciously crafted articles could attempt to influence the agent's behavior via embedded instructions.
Ingestion points: News article data and search results retrieved via the membrane action run command in SKILL.md.
Boundary markers: Not present; the instructions do not implement specific delimiters or 'ignore' instructions for the external content.
Capability inventory: The skill uses the CLI to execute actions (action run) and dynamically create new logic (action create) as seen in SKILL.md.
Sanitization: No explicit validation or filtering of article content is documented.

newslit