alterlab-vaex

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests arbitrary external data and state files (e.g., vaex.open('s3://bucket-name/data.parquet') and df.state_load('state.json') shown in references/io_operations.md), meaning untrusted/user-provided content from public cloud/storage can be loaded and applied to the agent's processing pipeline and thus materially influence subsequent operations.