skill-writer

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

• Third-party content exposure detected (high risk: 0.70). This skill's runtime workflow (SKILL.md Step 2 + references/synthesis-path.md and references/source-discovery.md) explicitly directs the agent to collect and synthesize external sources — including upstream docs, public issue/PR threads and other web resources — and to use that provenance to make class/shape and authoring decisions, so untrusted/user-generated third‑party content can be ingested and materially influence subsequent actions.