alterlab-citation-graph
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate academic research tasks using a well-known public API (OpenAlex).
- [EXTERNAL_DOWNLOADS]: The Python script fetches metadata from
api.openalex.org. This is a well-known academic service and the interaction follows the API's 'polite pool' convention by including a contact email. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data (paper titles and metadata) from an external API. While this presents a theoretical attack surface, the data is used to populate structured files (GraphML, JSON) and a ranking table rather than being used to override agent instructions or influence critical logic flow.
Audit Metadata