openalex
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
openalex-skillpackage globally via the npm registry. It also enables downloading PDF files from external repository URLs provided by the OpenAlex API metadata. - [COMMAND_EXECUTION]: The skill operates by executing the
openalexcommand-line interface for metadata retrieval, citation tracking, and configuration management. - [INDIRECT_PROMPT_INJECTION]: The skill processes academic metadata from an external API, which presents a surface for indirect prompt injection.
- Ingestion points: Paper titles, abstracts, and author information are retrieved from the OpenAlex API and processed by the agent (evident in
SKILL.mdandreferences/output-formats.md). - Boundary markers: The instructions do not define clear boundaries or 'ignore' directives for content fetched from the API.
- Capability inventory: The agent can execute shell commands (
openalex), write files to the disk (PDF downloads), and perform network operations. - Sanitization: The skill does not mention any validation or filtering of the retrieved academic content before it is incorporated into the agent's context.
Audit Metadata