manage-architecture

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required runtime workflow runs architecture derived-module and then “Read {paths.readme} / {package_info path} / sample 2-3 source files” to extract prose, which can include README/source text authored by outsiders in the target repo; that text is then used to populate LLM enrichment fields (e.g., --responsibility, --reasoning).