env-management

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

• Third-party content exposure detected (high risk: 0.80). The skill includes curl commands that fetch Markdown from public URLs (e.g., https://fullstackrecipes.com/api/recipes/config-schema-setup and other fullstackrecipes.com endpoints), which are untrusted third-party web content the agent would ingest and thus could carry indirect prompt injection.