roboflow-batch-processing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
inference-cliandinference-cli[cloud-storage]Python packages. These are official tools provided by the vendor, Roboflow, for platform interaction. - [COMMAND_EXECUTION]: The documentation provides multiple shell commands for the
inferenceCLI to manage data staging and processing jobs. These are intended for user execution to drive the batch processing workflow. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data, creating an attack surface for indirect prompt injection.
- Ingestion points: Data is ingested from local directories, cloud buckets (S3, GCS, Azure), and external URLs via references files.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore content-embedded instructions in the media files.
- Capability inventory: The skill facilitates remote job creation and result export via official MCP tools.
- Sanitization: There is no evidence of local content sanitization before the data is processed by the workflow.
Audit Metadata