stress-field-surrogate

Warn

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The script scripts/stressd.py performs unsafe deserialization using torch.load with weights_only=False in the predict function.
  • Evidence: The instruction ck = torch.load(model, weights_only=False) allows the deserialization of arbitrary Python objects via the pickle module.
  • Impact: A maliciously crafted model file could execute arbitrary code when loaded by the skill.
  • Mitigation: Use weights_only=True and store metadata separately or ensure models only originate from verified sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data files without sufficient sanitization, presenting an attack surface for indirect prompt injection.
  • Ingestion points: The skill reads .npz datasets and image files in scripts/stressd.py via the train, predict, and fem commands.
  • Boundary markers: The skill lacks boundary markers or specific instructions to the agent to ignore embedded instructions in the processed data.
  • Capability inventory: The skill has the ability to write to the file system using torch.save, np.savez_compressed, np.save, and matplotlib.pyplot.savefig.
  • Sanitization: There is no validation or sanitization of the input data content before it is processed or used in results.
  • Mitigation: Implement strict schema validation for data files and use delimiters or safety instructions when the agent interacts with processed data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 7, 2026, 06:03 AM