fusion-issue-solving

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly reads GitHub issue bodies, labels, and linked discussions as part of its required workflow (see SKILL.md step 2 and "Required inputs"), which are untrusted, user-generated third-party contents that the agent will interpret to decide implementation steps and perform actions, enabling indirect prompt injection.