datamol

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports reading remote/untrusted data (e.g., dm.read_csv("https://example.com/data.csv") and remote file support via fsspec for s3://, gcs:// and http(s) URLs) and the agent is expected to parse and process those external files as part of its workflows, exposing it to untrusted third‑party content.