external-llm-consulting

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs external LLM CLIs (Codex/Gemini) and parses their responses as part of its workflow—see "Execute the external CLI in read-only/sandbox mode" and "Parse and structure the response for comparison" in SKILL.md—so it ingests untrusted third‑party model outputs that can influence decisions.