crypto-onchain-data

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

• Third-party content exposure detected (high risk: 0.85). The required workflow runs onchain_fetch.py, which fetches outsider-authored free text/JSON from the public API https://bitcoin-data.com/v1/*/last via urllib.request.urlopen, and then injects the returned metric values (prose/JSON-derived strings) into the agent’s LLM context.