The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is the official command-line interface provided by the vendor for managing integrations.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform various tasks, including authenticating users, searching for connectors, and executing actions against the ThinQ API.
[DATA_EXFILTRATION]: Communication with the ThinQ API is performed via a proxy service (membrane request). This design allows the platform to manage authentication headers and token refreshes server-side, preventing the exposure of API keys in the local environment.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes and displays data fetched from the external ThinQ API.
Ingestion points: Untrusted data enters the agent context through the output of CLI commands like membrane action run and membrane request (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions to wrap the external API data.
Capability inventory: The agent has the capability to execute shell commands via the membrane CLI and make further network requests through the proxy.
Sanitization: There is no explicit evidence of content validation or sanitization performed on the API responses before they are processed by the agent.

thinq