The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from the npm registry. This is the official command-line interface provided by the skill's author (Membrane) and is considered a trusted vendor resource.
[COMMAND_EXECUTION]: The instructions rely on the agent executing membrane CLI commands to perform tasks such as authentication (membrane login), connecting to services (membrane connect), and running actions (membrane action run). This is the intended operational model for the skill.
[PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface because it retrieves and processes data from external sources (Fibery workspaces).
Ingestion points: Data is ingested through actions like get-document, get-entity-by-id, and query-entities as described in SKILL.md.
Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions found within the retrieved data.
Capability inventory: The skill possesses write capabilities including update-document, create-entity, update-entity, and delete-entity.
Sanitization: No specific sanitization or validation logic is defined in the documentation for handling data retrieved from Fibery.

fibery