The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is a vendor-owned resource necessary for the skill's operations.
[COMMAND_EXECUTION]: The skill uses shell commands through the membrane CLI to authenticate, manage connections, and execute actions within the Chatlayer environment.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting and processing data from external sources (Chatlayer).
Ingestion points: Chatlayer training data, intents, entity values, and user utterances (SKILL.md).
Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted data from the agent's instructions.
Capability inventory: The skill can list, create, and run actions (membrane action run), which could be influenced by malicious content in the training data or utterances.
Sanitization: No sanitization or validation logic is specified for the external data before it is processed by the agent.

chatlayer