marketer-localize-campaign

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow ingests outsider-authored free text via the user-provided “Translated copy per locale” (and per-job prompts that include that copy) into the LLM context; since the SKILL.md instructs the operator to paste translations from a copywriter/vendor (i.e., not authored by the operating user), this is an outsider source path.