The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data to generate document content.
Ingestion points: The process consumes data from papers/ideation_output.json, papers/experiment_blueprint.json, and files within the experiments/ directory.
Boundary markers: There are no defined delimiters or instructions provided to the agent to treat these inputs as pure data or to ignore embedded instructions.
Capability inventory: The skill utilizes tools such as generate_latex, compile_pdf, and generate_figure to create files and compile documents on the local system.
Sanitization: The instructions do not specify any validation, escaping, or sanitization of the input data before it is interpolated into the paper generation process.

nanoresearch-writing