openalex-database
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches scholarly metadata from api.openalex.org, which is a well-known and recognized service in the academic community for scholarly indexing.
- [INDIRECT_PROMPT_INJECTION]: Ingesting external data from the OpenAlex API creates a potential attack surface where malicious text in academic abstracts could influence agent behavior.
- Ingestion points: Untrusted data enters the agent context through API responses from api.openalex.org as seen in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters used to separate the external data from the agent's internal logic.
- Capability inventory: The skill uses pandas to write data to local CSV files (drug_repurposing_literature.csv, collaboration_network.csv) as described in SKILL.md.
- Sanitization: The code snippets do not include sanitization or validation of the text content retrieved from the database.
Audit Metadata