hf-cloud-sagemaker-deployment-planner
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution: The skill contains a pre-formatted AWS CLI command intended to query service quotas. This allows the agent to verify hardware availability before attempting a deployment, which is a standard step to prevent common resource limit errors during cloud provisioning.
- Infrastructure Planning Logic: The instructions define specific criteria for choosing between different deployment pathways, such as real-time endpoints or asynchronous inference. This conditional logic is focused on optimizing cost and performance for the user's workload.
- Data Ingestion Surface: The skill processes external information, such as model identifiers and infrastructure requirements provided by the user.
- Ingestion points: User input and environment context gathered in the discovery phase (SKILL.md).
- Boundary markers: Explicit instructions guide the agent to ask clarifying questions and confirm details before proceeding, though formal data delimiters are not present in the markdown text.
- Capability inventory: Use of the
awsCLI for metadata queries. - Sanitization: The skill relies on standard agent behavior for input validation; no specialized sanitization logic is implemented within the markdown instructions.
Audit Metadata