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
jfCLI andcurlto 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
jfCLI 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 thecontext.clients.platformHttpclient. - 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 deployandcurloperations. - Sanitization: The example templates do not demonstrate explicit sanitization or validation of the metadata retrieved from platform APIs.
Audit Metadata