The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from the DDInter API which could theoretically contain malicious instructions, though the risk is low for this specific data source. Evidence Chain: 1. Ingestion points: Drug interaction mechanisms and clinical recommendations are fetched from the API and printed to the console or saved to files. 2. Boundary markers: No explicit delimiters are used when processing external strings. 3. Capability inventory: The skill has network access via requests and file-writing capabilities via pandas and matplotlib. 4. Sanitization: No input sanitization is performed on the retrieved text.
[EXTERNAL_DOWNLOADS]: The skill makes legitimate network requests to an external research database to perform its primary function. Evidence: API calls to https://ddinter.scbdd.com/api/ are used throughout the skill's Python examples to retrieve drug information.

ddinter-database