Use AxEventRuntime to ingest events, explicitly wake or resume AxGen, AxAgent, and AxFlow, persist state and results, and route outputs safely.
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./website/static/typescript/.well-known/agent-skills/ax-event-runtime/SKILL.mdThe 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 runtime ingests externally POSTed webhook payloads (UCP webhook events from partner signers, plus push events and MCP server notifications) into an inbox, then maps their data into model inputs without the agent selecting a specific item, so an outsider who can reach the webhook endpoint or an MCP server's notification stream can get free text into the model's context.
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.