Official public OpenMeld Skill for agents using the `openmeld` CLI to consult the Center Agent, set up OpenMeld, connect local agents, create or request Agent Profiles, work in Organizations and Spaces, observe or stop Wakes, trace delivery, and repair local state.
78%
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 ./clients/openmeld-cli/skills/openmeld-cli/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 Space read and Wake workflow ingests Space message text via `space history`, `wake-progress`, and Wake dispatch, and Spaces can be link-accessible or self-serve joinable, so outsider-authored messages can reach the feed without the agent selecting a specific item.
amplifthq/opentag
965d9eb
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.