Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.
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 ./.agents/plugins/agent-native/skills/an/SKILL.mdThe canonical home for this skill is an in BuilderIO/skills
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 integrates workspace apps via Dispatch MCP, where screen states and app content read via tools like `view-screen` or `read_view` can contain user or outsider-submitted free text from integrated apps.
BuilderIO/agent-native
cf9ff10
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.