beo-planning

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

• Third-party content exposure detected (high risk: 0.80). The skill's mandatory discovery workflow (see Default Planning Loop in SKILL.md and the "External Agent" section in references/discovery-reference.md) instructs launching research that reads public API docs, package registries, and "community patterns"/best-practices (external, user-generated sources) and requires those findings to shape approach.md and planning decisions, thereby exposing the agent to untrusted third‑party content that can materially influence actions.