JFrog Workers

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the jf CLI and curl to manage the lifecycle of serverless functions, including initialization, testing, and deployment to the JFrog Platform.
  • [EXTERNAL_DOWNLOADS]: The skill mentions the automatic installation of the jf CLI tool if it is missing from the environment, ensuring the required vendor tooling is available for execution.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and act upon data from external sources within the JFrog Platform.
  • Ingestion points: Data enters the agent's context through worker scripts (e.g., worker.ts) which fetch artifact metadata and properties via the context.clients.platformHttp client.
  • Boundary markers: No specific boundary markers or instructions to ignore instructions within the ingested data are present in the provided templates.
  • Capability inventory: The skill enables the creation and deployment of executable code to the platform via jf worker deploy and curl operations.
  • Sanitization: The example templates do not demonstrate explicit sanitization or validation of the metadata retrieved from platform APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 03:44 PM