alterlab-pymatgen

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests data from the public Materials Project via the mp-api (see "Materials Project Integration" and "Materials Project Database Access" in SKILL.md and the scripts/scripts/phase_diagram_generator.py which uses MPRester to retrieve entries), and that external data is parsed and used to drive analyses and decisions (phase-diagram building, stability checks, decomposition, etc.), so untrusted third‑party content can materially influence workflow.