orchestrate-multi-target-sdks

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to use the speakeasy CLI for project initialization, source configuration, and SDK generation. These are standard operations for the tool's intended use.
  • [EXTERNAL_DOWNLOADS]: The documentation provides an example GitHub Action workflow that uses the speakeasy-api/sdk-generation-action. This is an official resource provided by the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves processing OpenAPI documents from local paths or remote URLs, which constitutes an ingestion point for external data. This is a standard part of the SDK generation workflow.
  • Ingestion points: External OpenAPI specifications referenced via the --location flag in the speakeasy configure sources command.
  • Boundary markers: Not present in the provided instructions; the tool processes the document content directly.
  • Capability inventory: The skill uses the CLI to generate code and manage project files in the local workspace.
  • Sanitization: No specific sanitization instructions are provided in the skill text, as the logic resides within the Speakeasy CLI tool itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:45 PM
Security Audit — agent-trust-hub — orchestrate-multi-target-sdks