Safe-use reference for the optional Aside browser agent (the `aside` command-line tool and its MCP server), which works inside the operator's own logged-in browser. Covers when the orchestrator may use it, how its permission modes work, and the rules that keep it read-only by default. Operated by the orchestrator alone. NOT for: public pages that a plain fetch can read, subagent work, or CI runs.
87%
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
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 describes an optional browser agent that navigates web pages selected by the operator or agent, falling under low indirect prompt injection risk from arbitrary web content.
modu-ai/moai-adk
4fa2aa9
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.