hyprland

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly loads and searches local copies of documentation that were fetched from the public Hyprland wiki (references/docs/ sourced via r.jina.ai from https://wiki.hypr.land) and even includes curl commands in SKILL.md to refresh those files from that open web source, so the agent is expected to read and act on third‑party web content as part of its workflow.