The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides capabilities to ingest untrusted data from an external OMERO server, including image metadata, tags, map annotations, and file attachments.
Ingestion points: references/metadata.md, references/data_access.md, and references/tables.md describe methods to retrieve data from the server.
Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from interpreting instructions found within retrieved metadata.
Capability inventory: The skill includes file system write access (references/metadata.md, references/advanced.md), network connectivity to arbitrary hosts (references/connection.md), and pixel data manipulation.
Sanitization: No sanitization or validation of the content retrieved from the OMERO server is mentioned.
[COMMAND_EXECUTION]: The documentation provides instructions for installing the omero-py library using pip and mentions using the omero command-line interface for script deployment and testing.

omero-integration