syncing-submodules

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests content from git submodules (Phase 1, e.g., "git submodule update --remote --merge" and scanning submodules/* for SKILL.md and other *.md files), which are arbitrary external repositories whose user-generated markdown the agent then reads and semantically analyzes—exposing it to untrusted third‑party content and potential indirect prompt injection.