matchms

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly supports loading spectra from public repositories (e.g., load_from_usi(usi) — Universal Spectrum Identifier — and GNPS/JSON imports noted in references/importing_exporting.md), which fetches untrusted, user-generated spectral data and metadata that the agent is expected to read and process.