task-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill includes multiple task templates that accept and fetch arbitrary external URLs and return/parse their responses (e.g., templates/api-task.py: api_call_with_retry, paginated_api_fetch, batch_api_calls, webhook_delivery; templates/pydantic-validation.py: make_api_call/ApiRequest; examples/task-with-retries.md: fetch_api_data), so the agent would ingest and interpret untrusted, user-provided third-party content.