The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to install the @membranehq/cli package from npm. This is the official CLI tool provided by the platform vendor (Membrane).
[COMMAND_EXECUTION]: The skill relies on shell commands executed via the membrane CLI to manage connections and interact with the Lattice API. These commands are necessary for the skill's intended functionality.
[PROMPT_INJECTION]: The skill defines an indirect prompt injection surface by processing data from an external source (Lattice).
Ingestion points: Untrusted data is ingested when the agent retrieves feedback, notes, and user-generated content from the Lattice API using actions like get-feedback and list-updates.
Boundary markers: No specific delimiters or boundary instructions are provided to help the agent distinguish between its instructions and the data being processed.
Capability inventory: The agent can perform significant actions via the membrane action run and membrane request tools, which could be triggered by instructions embedded in the ingested data.
Sanitization: The skill does not mention any sanitization or validation processes for the data fetched from the external API.

lattice