CLI harness for the Mailchimp Marketing API v3.0 — 303 commands across 30 resource groups (lists, campaigns, reports, automations, ecommerce, templates, and more). Supports JSON output and interactive REPL mode.
72%
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 ./mailchimp/agent-harness/cli_anything/mailchimp/skills/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 Mailchimp CLI skill reads audience lists, subscriber names/emails, campaign reports, and customer data which can contain user-submitted outsider text.
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 installation instructions use `pip install` with a GitHub repository URL (https://github.com/HKUDS/CLI-Anything.git) to download and install the package at runtime, presenting a third-party/community dependency with unknown or common unofficial provenance.
HKUDS/CLI-Anything
34f5195
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.