pylabrobot

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of the pylabrobot package from the Python Package Index (PyPI), which is the primary library for the automation functionality described.
  • [COMMAND_EXECUTION]: The provided Python code examples demonstrate the execution of commands to initialize and control physical laboratory hardware, including Hamilton STAR, Opentrons OT-2, and various analytical devices.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface through its ability to ingest external configuration data.
  • Ingestion points: The Deck.load_from_json_file and load_state methods in references/resources.md allow the skill to load deck layouts and resource states from JSON files.
  • Boundary markers: No specific boundary markers or warnings against embedded instructions in the JSON data are mentioned in the documentation.
  • Capability inventory: The skill possesses high-impact capabilities, including physical control of liquid handlers, centrifuges, and heater shakers, as well as network communication with robots via HTTP APIs.
  • Sanitization: The reference materials do not explicitly detail sanitization or validation protocols for the imported JSON configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 12:15 PM