The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the Membrane CLI tool (@membranehq/cli) globally via the npm registry. As this tool is provided by the vendor, this is a standard and expected operation.
[COMMAND_EXECUTION]: The skill executes various membrane CLI commands to manage authentication, connection state, and to trigger actions or proxy requests to the UiPath API.
[INDIRECT_PROMPT_INJECTION]: The skill uses natural language search for actions, creating a potential surface for indirect prompt injection where user input influences the tool selection process.
Ingestion points: User-provided queries are passed directly to the --intent parameter of the membrane action list command in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore commands within the user intent string.
Capability inventory: The skill possesses the capability to execute discovered actions and send arbitrary HTTP requests via the membrane request command.
Sanitization: There is no evidence of validation or sanitization for the input passed to the intent search or action parameters.

uipath