The Agent Skills Directory

[SAFE]: The skill interacts with the OpenAlex REST API at https://api.openalex.org. OpenAlex is a well-known, legitimate service for academic metadata. The network operations are transparent and consistent with the skill's stated purpose.- [SAFE]: The skill instructs the user to install requests and pandas using pip. These are standard, widely-trusted Python libraries for handling HTTP requests and data analysis.- [PROMPT_INJECTION]: The skill processes external data (scholarly titles, abstracts, and author information) fetched from the OpenAlex API, which serves as an ingestion point for untrusted content into the agent's context.
Ingestion points: Data is fetched via requests.get calls in multiple Python examples within SKILL.md (e.g., Quick Start, search_works, Author Search).
Boundary markers: The code examples do not implement delimiters or specific instructions to the agent to ignore potentially malicious content within the fetched data.
Capability inventory: The skill utilizes requests for network communication and pandas for data manipulation, including writing to files (e.g., df.to_csv).
Sanitization: There is no evidence of input validation, filtering, or sanitization performed on the content retrieved from the external API before it is processed or displayed.

openalex-database