obsidian-ref

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

• Third-party content exposure detected (high risk: 0.90). The skill's references/ref-instructions.md "For AI Agents" section explicitly instructs agents to search the .ref folder and to clone/fetch/check external GitHub repos (e.g., git clone https://github.com/username/...), read repository files and git logs, and report changes—so the agent will routinely ingest and act on untrusted, user/community-provided third‑party content that can influence its actions.