pulumi-cli
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to run Pulumi CLI commands that manage cloud resources. It suggests the use of
--yesandPULUMI_CI=truefor automation, which allows high-impact commands such as stack removal or resource deletion to run without interactive approval. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection when handling external files.
- Ingestion points: The
pulumi import --fileandpulumi stack import --filecommands read JSON data from external files. - Boundary markers: No explicit instructions are provided to ensure the agent ignores natural language prompts within these files.
- Capability inventory: The skill allows the execution of powerful Pulumi commands that can significantly alter cloud environments.
- Sanitization: No validation or sanitization process for the JSON file content is specified.
Audit Metadata