honi
Build AI agents with Honi (honidev) on Cloudflare Workers. Use when creating agents with tools, persistent memory, MCP servers, or multi-agent pipelines. Covers createAgent API, tool() helper, all memory tiers (working/episodic/semantic/graph), multi-agent routing, MCP auth, and all supported model providers.
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The skill is documentation for a legitimate framework, but its README tells users to run `curl -o CLAUDE.md`, which silently overwrites any existing project CLAUDE.md, a careless destructive step.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
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.
Why it was flagged
Setup instructions in README.md fetch the skill from a third-party repository (fluxwiseai/honi-skill, not the Honi project's stukennedy/honi) and the fetched SKILL.md is adopted as instructions for Claude, so this is an unofficial but reputable-looking dependency with no concrete warning signs, rated medium.
- Repository
stukennedy/honi-skill
- Path
SKILL.md
- Revision
d61c6be
- Audited
- Security analysis
Is this your skill?
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.