i4h-workflow-dataset-replay

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Clones the i4h-workflows repository from https://github.com/isaac-for-healthcare/i4h-workflows. Note: Isaac for Healthcare (i4h) is an official NVIDIA organization, qualifying as a trusted source.
  • [COMMAND_EXECUTION]: Executes local scripts using python and bash (e.g., workflows/agentic/tools/replay_hdf5.py) within a .venv environment.
  • [INDIRECT_PROMPT_INJECTION]: Processes external HDF5 recording files which could serve as a vector for indirect injection if metadata or data fields are manipulated, though risks are limited to visual replay.
  • [METADATA_POISONING]: The evals/evals.json file references an external environment astra-sandbox. This indicates the skill is intended to interact with or was evaluated against external data/infrastructure, which constitutes a vulnerability surface for indirect instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:49 AM
Security Audit — agent-trust-hub — i4h-workflow-dataset-replay