coding

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md describes a coding workflow where the agent answers “how should I write this now” by verifying against “official docs… then the open web” (runtime browsing/search/content reading is explicitly contemplated), which can ingest outsider-authored free text from the web feed/page content.