short-form-brief

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

• Third-party content exposure detected (high risk: 0.90). The skill's orchestrator and agents explicitly require reading the per-platform research catalog (.agents/skill-artifacts/research/short-form-research.md) and platform-intelligence/reference files (e.g., references/platform-intelligence/linkedin.md) — documents that include and reference public web posts/URLs — and those excerpts are passed into format-agent, hook-agent, audio-agent, platform-tailor-agent, and the critic to drive decisions, so untrusted third-party content is consumed and can materially influence agent behavior.