The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill adheres to security best practices by delegating authentication and credential management to the Membrane platform.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package via npm. This is a recognized vendor resource required for the skill's operation.
[COMMAND_EXECUTION]: Instructions involve using the membrane CLI for managing connections and executing actions. These commands are part of the intended integration workflow.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes external data from Cohere APIs.
Ingestion points: Data returned by membrane action run and membrane request (SKILL.md).
Boundary markers: No specific delimiters or warnings for embedded instructions are provided in the tool documentation.
Capability inventory: Access to CLI commands for running actions and making proxy requests (SKILL.md).
Sanitization: No explicit sanitization or validation of the external API responses is mentioned.

cohere