Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/workflow/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is legitimate Vercel Workflow SDK guidance, but it hard-codes an unverifiable "spacexai/grok-4.6" model as the default across examples and steers the agent away from direct provider setup, which could route the user's AI calls to an unexplained vendor without their knowledge.
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 required workflow reads first-party Workflow SDK docs and CLI/World run data (step I/O via `world.steps.list` and `hydrateResourceIO`) during debugging, and that run data can contain payloads from external callers of the user's own app, but the skill itself does not monitor an outsider-writable queue, so this is at most a low-risk exposure that requires the agent to actively select runs.
vercel/vercel-plugin
8a9039d
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.