skill-tree-generator

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to read raw library documentation, source code, changelogs and repo files (see "Prerequisites" — "Raw library documentation and source code" — and the required sources: frontmatter entries like "[Owner/repo]:docs/[path].md"), which are untrusted public third‑party contents the agent must ingest and whose content can change generation/update decisions.