base-in-reality

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries scholarly academic APIs (arXiv, PubMed, Crossref, OpenAlex, Semantic Scholar) and external URLs via WebSearch/WebFetch to verify code claims, which constitutes fetching outsider-authored literature and web content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill's bundled helper script queries external scholarly APIs (arXiv, PubMed, Crossref, OpenAlex, Semantic Scholar) using hardcoded URLs during runtime setup/execution, satisfying the operational dependency gate under common/reputable unofficial provenance.