The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions designed to influence the agent's behavior during search or questioning operations.
Ingestion points: Local files and directories provided via mxbai store upload and mxbai store sync (e.g., docs/**/*.md, reports/*.pdf).
Boundary markers: The instructions do not specify the use of delimiters or specific system prompts to ignore instructions embedded within the uploaded documents.
Capability inventory: The CLI can create stores, upload/sync files, perform semantic searches, and query documents via the mxbai store search and mxbai question commands.
Sanitization: No explicit sanitization or filtering of document content is mentioned before it is ingested into the Mixedbread platform.
[EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install the @mixedbread/cli package from the npm registry. As this package is the official tool from the skill's author (mixedbread-ai), the download is considered a standard operation.
[COMMAND_EXECUTION]: The skill defines several command-line workflows for managing configuration, environment keys, and document synchronization, which are executed in the local shell environment.

mxbai-cli