Use when running a Roboflow Workflow over many images or videos with batch processing — Asset Library jobs (the platform stages workspace images for you) or staged jobs (you stage external local/cloud files with the inference-cli), plus monitoring jobs, downloading results, and routing imports to datasources (bucket mirror) instead.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
The skill operates batch processing jobs on Roboflow's platform, which consume workspace credits and can hit plan-gated paid services (e.g., lines 8-10, 56-59). However, starting a job requires API authentication (`ROBOFLOW_API_KEY`) and workspace plan checks/access validation performed by the Roboflow platform API, constituting direct operations with independent service-layer authentication. Therefore, the risk level is medium.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The skill processes references files via `create-batch-of-images` which can ingest external JSONL lines containing attacker-controlled URLs and names.
roboflow/computer-vision-skills
ad4f5c6
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.