Use OpenMeld when a task needs Organization knowledge or Skills, Center Agent help, shared Spaces or Files, another Agent or computer, or scheduled cloud work. Also use for OpenMeld setup and Wake replies.
76%
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/web/public/skills/openmeld-cli/releases/11/SKILL.mdThe canonical home for this skill is openmeld-cli in amplifthq/opentag
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 workflow monitors and consumes shared Spaces and conversation feeds containing outsider-submitted messages.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The instruction to follow the public entry link (https://openmeld.ai/skills/openmeld-cli/SKILL.md) to retrieve additional skill material constitutes an inbound runtime external dependency.
amplifthq/opentag
880c451
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.