The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires users to install the flow-nexus package from the npm registry using the npx utility. This introduces a dependency on external code that is executed during the setup process. Evidence includes the prerequisite command npx flow-nexus@latest mcp start and registration commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external datasets and inference inputs, creating a surface for indirect prompt injection if the ingested data contains malicious instructions targeting the AI agent. * Ingestion points: Data enters the system through the dataset parameter in the mcp__flow-nexus__neural_train_distributed tool and the input parameter in the mcp__flow-nexus__neural_predict tool. * Boundary markers: The instructions do not provide specific delimiters or warnings to the agent to treat external dataset content as untrusted. * Capability inventory: The skill has the capability to deploy worker nodes, manage distributed clusters, and execute model training or inference jobs. * Sanitization: There is no mention of sanitization, validation, or integrity checking for the input datasets used for training or prediction.

flow-nexus-neural