alterlab-polars

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

• Third-party content exposure detected (high risk: 0.70). The skill's I/O documentation (references/io_guide.md and SKILL.md) instructs the agent to read data from external locations such as s3://, az://, gs://, BigQuery and arbitrary database URIs, which are third-party/untrusted data sources that the agent is expected to load and whose contents can materially influence analysis and subsequent actions.