openalex

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The agent skill retrieves academic metadata and scholarly work via the OpenAlex CLI and API, which involves ingesting community-published research papers, abstracts, and metadata where an attacker can publish content (scored as low).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of the openalex-skill package via npm install -g openalex-skill, which pulls third-party code from the public npm registry without a verifiable publisher provenance or integrity guarantee, representing a weak/unknown runtime dependency.