The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm. This is the official command-line interface for the Membrane platform and is necessary for the skill's functionality.
[COMMAND_EXECUTION]: The skill documentation provides various membrane command examples to search for connectors, manage connections, and execute actions. These commands are part of the intended workflow for interacting with the Paigo service through the Membrane proxy.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill emphasizes security by explicitly advising against asking users for API keys or tokens, instead utilizing Membrane's server-side connection management to handle authentication safely.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it retrieves and processes records from the Paigo API. While this presents a theoretical surface for indirect prompt injection if the external data contains malicious instructions, the risk is considered low and managed by standard model guardrails.
Ingestion points: Data retrieved from Paigo API via membrane action run or membrane request (documented in SKILL.md).
Boundary markers: None explicitly defined in the prompt instructions.
Capability inventory: The skill uses the membrane CLI to execute actions and network requests (SKILL.md).
Sanitization: No explicit sanitization or filtering of API responses is mentioned in the instructions.

paigo