The Agent Skills Directory

[SAFE]: The skill implements strong security defaults for deployment, including binding the service to localhost (127.0.0.1) and requiring a master key in production environments to prevent unauthorized access.
[SAFE]: Provides clear guidance on secret management by recommending the use of openssl for secure key generation and utilizing environment variables for external credentials.
[SAFE]: Promotes secure multi-tenancy by demonstrating how to generate scoped tenant tokens, which prevents data exposure between different users or organizations.
[SAFE]: Recommends fetching binaries from official GitHub releases rather than using potentially unsafe pipe-to-shell installation methods.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of arbitrary data into a search index, which represents a potential attack surface if the retrieved content is processed by an LLM without proper sanitization.
Ingestion points: Document indexing via the REST API and Node.js SDK in SKILL.md.
Boundary markers: Not present.
Capability inventory: Data indexing and search retrieval operations.
Sanitization: Relies on external application logic to handle search results securely.

meilisearch