The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official NPM registry to manage the integration with the Membrane platform.
[COMMAND_EXECUTION]: The skill uses the membrane command-line interface to perform authentication, discover available actions, and execute data operations against the Procountor API.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting and processing data from the external Procountor financial system.
Ingestion points: Untrusted data enters the agent context through the output of membrane action run commands as described in SKILL.md.
Boundary markers: There are no specific delimiters or instructions provided to the agent to isolate or ignore embedded instructions within the retrieved financial data.
Capability inventory: The skill utilizes subprocess calls to the membrane CLI in SKILL.md for both data retrieval and action execution.
Sanitization: No sanitization or validation of external content is specified before the data is processed by the agent.

procountor