The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry and occasionally uses npx to run the latest version of the CLI directly.
[COMMAND_EXECUTION]: Employs the membrane command-line interface to manage authentication (login), establish service links (connect), and interact with financial data endpoints (action run, request). These are legitimate operations for the skill's stated purpose.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted external data from financial transaction histories and bank statements.
Ingestion points: Data enters the agent context via the output of membrane action run and membrane request commands in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent processes the retrieved financial data.
Capability inventory: The skill has the ability to execute shell commands via the Membrane CLI and make network requests.
Sanitization: There is no explicit sanitization or validation logic described for the data retrieved from the Kontomatik API before it is processed by the agent.
[SAFE]: The skill author ('membrane') provides their own official CLI and infrastructure. All external resources and domains (getmembrane.com, @membranehq/cli) are verified vendor resources, representing standard and transparent functionality.

kontomatik