data-pipelines

Warn

Audited by Snyk on Feb 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly instructs using dlt to ingest from REST APIs (example rest_api_source with base_url "https://api.example.com/v1") and DuckDB to read external files/S3 ('s3://bucket/path/*.parquet'), so the agent is expected to fetch and interpret arbitrary external/public API and file content that can materially influence downstream transforms and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 09:51 PM