The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to run the neuroskill utility, which involves downloading the package from the npm registry if it is not present locally. As this is a first-party tool from the skill author, it represents intended functionality.
[COMMAND_EXECUTION]: Extensive use of shell commands via npx neuroskill to interact with the local BCI server. Commands include retrieving system status, searching historical neural embeddings, and triggering OS notifications.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by ingesting biometric metrics and user-supplied labels from a local SQLite database.
Ingestion points: npx neuroskill status, npx neuroskill search-labels, and npx neuroskill interactive commands return data from the local BCI environment.
Boundary markers: No explicit delimiters are used in the prompt instructions when interpolating the JSON response from the CLI.
Capability inventory: The skill possesses the ability to execute shell commands and write to the local database via the label command.
Sanitization: The instructions do not define methods for sanitizing retrieved text labels before they are processed by the agent.

neuroskill-bci