The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the public NPM registry. This is a vendor-owned resource used to interact with the Membrane platform.
[COMMAND_EXECUTION]: The instructions utilize the membrane CLI to perform authentication, create connections, search for actions, and execute them against the Ironclad API.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes potentially untrusted data from the Ironclad platform.
Ingestion points: Data enters the agent's context through the output of commands like membrane action run and membrane action list.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external contract data as untrusted or to ignore instructions embedded within it.
Capability inventory: The skill provides full shell access via the membrane CLI across multiple scripts and instructions, allowing the agent to perform connection management and action execution.
Sanitization: There is no evidence of sanitization or validation of the data retrieved from Ironclad before it is processed by the agent.

ironclad