celery-expert

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

• Third-party content exposure detected (high risk: 1.00). The skill includes tasks that fetch and parse arbitrary external URLs (e.g., fetch_data.s('https://api.example.com/data') and call_external_api(self, url) which uses requests.get(url) and response.json()), so it clearly ingests untrusted public third‑party content that the agent would read and interpret.