pulumi-component

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill describes the use of pulumi package add, which downloads provider plugins and generates SDKs from remote Git repositories or the Pulumi Registry. This is a core feature of the Pulumi ecosystem for sharing reusable infrastructure components.
  • [COMMAND_EXECUTION]: The documentation provides examples of various CLI commands used for managing infrastructure and publishing packages, including pulumi up, pulumi package add, pulumi package publish, npm publish, and twine upload.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines argument interfaces that accept external configuration data via Input<T> types. This creates an ingestion surface for data-driven interactions with cloud provider APIs.
  • Ingestion points: Component constructor argument interfaces defined in SKILL.md.
  • Boundary markers: None explicitly mentioned in the provided code patterns.
  • Capability inventory: Cloud resource management (S3, ECS, SNS, etc.) and execution of Pulumi CLI operations.
  • Sanitization: Relies on Pulumi's internal type system and provider-side validation of resource properties.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:32 PM
Security Audit — agent-trust-hub — pulumi-component