Load when reviewing a diff, classifying findings, or returning a verdict.
67%
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/reviewer/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 QA workflow reads GitHub issue bodies and comments via `gh issue view ... --json body,comments` (any outsider can post a comment), and the review workflow reads PR-branch diffs and code comments authored by any contributor, so outsider free text enters the required runtime path without the agent selecting a specific item.
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 `kendex add vanillagreencom/kendex` install command in README.md is an instructed setup fetch of installed skill material from a GitHub repository, but the publisher is an unverified project organization rather than a recognized vendor, so it is a common/reputable unofficial dependency.
vanillagreencom/kendex
568be42
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.