The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the hypogenic package and clone research datasets from the ChicagoHAI GitHub organization. These actions are part of the setup for its intended scientific discovery functionality.
[INDIRECT_PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection by processing external content and including it in LLM prompts.
Ingestion points: The framework reads data from training, validation, and test JSON files, as well as literature research papers in PDF format.
Boundary markers: Prompt templates in the config_template.yaml file use direct variable interpolation (e.g., {sample_text}, {observations}) but do not include explicit delimiters or system instructions to ignore potentially malicious commands within that data.
Capability inventory: The skill uses the ingested data to generate scientific observations and hypotheses, and to perform inference tasks through an LLM.
Sanitization: There is no evidence of input validation, filtering, or escaping of the external content before it is interpolated into the prompts for completion.

hypogenic