tooluniverse-inorganic-physical-chemistry
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts to perform chemistry calculations. This includes its own script
equilibrium_solver.pyand fallback scripts located in a peer skill directory (tooluniverse-organic-chemistry). These commands are used for scientific calculations such as crystal structure validation and equilibrium solving. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted user data—such as crystal lattice parameters, stoichiometries, and equilibrium constants—which are then interpolated into command-line arguments for Python scripts. The
equilibrium_solver.pyscript provides basic sanitization through theargparsemodule, which enforces type validation (float and integer) for the input parameters.
Audit Metadata