agent-lifecycle-manager

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

• Third-party content exposure detected (high risk: 0.80). The skill's Discover workflow (SKILL.md Phase 2) and the Research Handoff guidance (references/research-handoff.md and eval cases like eval-5) explicitly delegate to helpers such as "researcher"/"docs-researcher" to fetch and synthesize external official and community sources (public web/community examples), and skill.json grants network capability—so untrusted third-party content can be ingested and used to influence authoring decisions.