NYC

data-context-extractor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted data from external database schemas and user-uploaded files during its 'Iteration Mode', which could theoretically contain malicious instructions.
  • Ingestion points: Database schema discovery via ~~data warehouse tools and user-provided ZIP files/folders in 'Iteration Mode'.
  • Boundary markers: The skill uses structured Markdown templates and clear code block delimiters for generated content.
  • Capability inventory: The skill uses ~~data warehouse tools for reading metadata and includes a local Python script (package_data_skill.py) that performs file system writes (ZIP creation).
  • Sanitization: The provided Python script includes a validation step that checks for required frontmatter fields and ensures placeholder text has been replaced before packaging files.
  • [Command Execution] (SAFE): The skill includes a Python script (package_data_skill.py) for administrative tasks. The script uses standard libraries and performs legitimate file operations (reading, directory creation, and ZIP compression) consistent with its stated purpose of packaging documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:10 PM