opentrons-machine
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the read_csv_file functionality. Maliciously crafted CSV data could potentially influence the logic of the generated Python protocols. * Ingestion points: read_csv_file (SKILL.md and references/opentrons-machine.md) allows the ingestion of external data files. * Boundary markers: The instructions do not define clear delimiters or instruction-override protections for the data read from CSV files. * Capability inventory: The skill generates executable Python code and manages robot hardware operations (pipetting, camera capture). * Sanitization: There is no mention of sanitizing or validating the contents of the CSV files before they are used to interpolate protocol parameters.
- [COMMAND_EXECUTION]: The skill instructs the agent to run the puda machine commands opentrons CLI tool to retrieve available commands and parameters. This tool is a vendor-provided resource for the Opentrons machine.
Audit Metadata