The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the official NPM registry. This is the legitimate tool for interacting with the Membrane platform.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to perform actions like searching for connectors, managing connections, and running integration actions. These commands are local to the user's environment and used for their intended administrative purposes.
[DATA_EXFILTRATION]: While the skill involves network operations to Cloudflare R2 and Membrane's proxy, these are documented functional requirements for object storage management. The skill explicitly advises against manual credential handling, recommending Membrane's built-in OAuth/token management instead.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes data from Cloudflare R2.
Ingestion points: Data retrieved from Cloudflare R2 buckets through membrane action run or membrane request (SKILL.md).
Boundary markers: No specific boundary markers or 'ignore' instructions are provided for processed data.
Capability inventory: The skill can execute shell commands via the membrane CLI and perform network operations (SKILL.md).
Sanitization: No explicit sanitization or validation of data retrieved from external APIs is mentioned.

cloudflare-r2