specmint-core

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

• Third-party content exposure detected (high risk: 0.90). The skill's required forge/research workflow (see agents/researcher.md and SKILL.md / commands/forge.md) explicitly runs WebSearch/WebFetch and reads public web pages, GitHub and library docs as part of research, meaning the agent ingests untrusted third‑party content that can influence spec decisions and subsequent actions.