i4h-workflow-setup
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill clones the repository from
https://github.com/isaac-for-healthcare/i4h-workflowsto set up the agentic workflow environment. This is a vendor-owned resource used for the skill's primary setup purpose. - [REMOTE_CODE_EXECUTION]: The workflow involves downloading and executing shell scripts, such as
setup.sh,third_party/setup.sh, andpolicy/run.sh, from the cloned repository. - [COMMAND_EXECUTION]: The skill utilizes several standard Linux commands, including
git,nvidia-smi,df,mkdir, andln, to verify system requirements, manage directories, and prepare the execution environment. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill relies on the
I4H_WORKFLOWSenvironment variable and host-level output fromgit rev-parseto determine the working directory inSKILL.md. - Boundary markers: No specific boundary markers or "ignore embedded instructions" warnings are used when processing the path variables.
- Capability inventory: The skill has the capability to execute shell commands, perform file system operations, and conduct network requests via
git. - Sanitization: No explicit sanitization or validation is performed on the environment-derived paths before they are used in command strings.
Audit Metadata