i4h-workflow-setup
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill clones the workflow repository from 'https://github.com/isaac-for-healthcare/i4h-workflows' to set up the runtime environment. This targets a repository associated with the skill's authoring organization.
- [COMMAND_EXECUTION]: The skill executes multiple shell commands for system discovery and configuration, including 'nvidia-smi', 'uv', './setup.sh', and './run.sh'. These are used for host preflight and component installation.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read dependency and version requirements from the './README.md' file within the newly cloned repository. This creates a surface where content from an external file can influence the agent's logic.
- Ingestion points: './README.md' (for requirements) and './third_party/IsaacSim-045ca8b/skills/SKILLS.md' (for verification).
- Boundary markers: None present.
- Capability inventory: Shell command execution ('setup.sh', 'run.sh') and filesystem access.
- Sanitization: No validation or filtering is applied to the content of the external files before the agent processes them.
Audit Metadata