The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally via npm and utilizes npx to execute the latest version of the tool. These resources are provided by the vendor to enable the skill's core functionality.
[COMMAND_EXECUTION]: The skill relies on shell commands using the membrane CLI to perform various tasks, including user authentication (membrane login), connection management (membrane connect), and running integration actions (membrane action run).
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes data from external SaaS applications via the Integry platform.
Ingestion points: External data enters the agent's context through the output of membrane action run and membrane request commands.
Boundary markers: The instructions do not define specific delimiters or include warnings to the agent to disregard instructions embedded within the external data.
Capability inventory: The skill has the ability to execute actions in connected applications and perform arbitrary HTTP requests through the Membrane proxy, which could be exploited if malicious data influences the agent's behavior.
Sanitization: There is no evidence of sanitization, filtering, or validation of the data retrieved from external sources before it is presented to the agent.

integry