agent-review

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls agent_get { name } to fetch the target agent’s AGENTS.md frontmatter and markdown body, and that body is outsider-authored free text (by someone other than the operating user) that is then pasted into the sub-agents’ prompts/LLM context for the structure/quality checks.