ai-ml-data-science

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied JSON and JSONL specification files containing fields like feature names and descriptions, which are then interpolated into Markdown reports. This creates a surface for indirect prompt injection if the agent interprets the generated reports as instructions.
  • Ingestion points: The scripts ml_toolkit.py (via --input flag) and leakage_scan.py (via --spec flag) ingest data from local metadata files.
  • Boundary markers: The generated Markdown reports do not implement explicit boundary markers or security warnings to distinguish tool-generated structure from user-provided data.
  • Capability inventory: The toolkit includes file-system read/write capabilities and a test runner script (scripts/test_leakage_regressions.py) that utilizes subprocess.run to execute Python scripts.
  • Sanitization: User-provided strings from the input specifications are not sanitized or escaped before being placed into Markdown tables and descriptive sections.
  • [COMMAND_EXECUTION]: The script scripts/test_leakage_regressions.py uses the subprocess module to execute other scripts within the project for regression testing.
  • Evidence: The invoke function calls subprocess.run(args, ...) where args is constructed from the Python interpreter and local script paths.
  • Context: The command execution is used as a test runner for local validation of the toolkit's CLI functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 08:26 AM