Load for any coding or development task in any repository: writing, changing, fixing, refactoring, or testing code or scripts in any language.
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 ./.agents/skills/code-quality/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 workflow only reads local skill files and the agent's own repository, but SKILL.md:70 and :49 direct it to read the current documentation of whatever external system it integrates with, and the skill names no specific provider, so any outsider-authored third-party docs it fetches fall under the "selected docs" low category.
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 README's setup instruction (`kendex add vanillagreencom/kendex --skill code-quality`) fetches this skill's installed material from a GitHub repository, and the repository is owned by an individual-scale publisher with no strong first-party provenance, so it is a common/reputable unofficial dependency (medium).
vanillagreencom/kendex
3a2f84c
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.