i4h-workflow-dataset-annotate
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill clones the
i4h-workflowsrepository fromhttps://github.com/isaac-for-healthcare/i4h-workflows. This is a vendor-owned resource associated with the Isaac for Healthcare project. - [COMMAND_EXECUTION]: The skill executes orchestration and utility scripts (
vllm.shandrun.sh) located within the cloned repository to manage VLM serving and annotation tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes robotic recordings (HDF5) and environment configurations (YAML), passing task descriptions to a VLM for success classification. This represents a potential vulnerability surface if the processed data contains malicious instructions.
- Ingestion points: Reads task success criteria from
config/environments/<env>.yamland frame data from HDF5 files specified by theHDF5_PATHvariable. - Boundary markers: None identified; instructions do not explicitly define delimiters for external content within the VLM prompt.
- Capability inventory: Performs network requests to a VLM API endpoint (
VLM_BASE_URL), writes annotation results and logs to local storage, and executes shell scripts. - Sanitization: The skill does not document explicit sanitization or filtering of the task descriptions or HDF5 metadata before they are interpolated into the VLM workflow.
Audit Metadata