The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the NPM registry to facilitate platform interactions. This is a recognized vendor resource for the Membrane ecosystem.
[COMMAND_EXECUTION]: Shell commands are used via the membrane CLI to perform administrative tasks such as logging in, searching for connectors, and executing API actions. These operations are within the expected scope of a CLI-based integration.
[PROMPT_INJECTION]: The skill processes external data from the Placekey API, which presents a surface for indirect prompt injection.
Ingestion points: Data is ingested through the output of membrane action run and membrane request commands described in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions potentially embedded in the retrieved data.
Capability inventory: The skill possesses the capability to execute shell commands via the membrane CLI as documented in SKILL.md.
Sanitization: No specific sanitization or filtering logic for the API responses is mentioned in the instructions.
[SAFE]: Sensitive authentication tokens and API keys are managed server-side by the Membrane platform. The skill correctly instructs users to use connections rather than asking for or storing local secrets, minimizing the risk of credential exposure.

placekey