Load to render, check, or adopt a repo's GitHub review-bot instruction files from the shared doctrine and its effective manifest.
70%
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 ./skills/bot-instructions/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 render and check runs read the spec copy's doctrine and surfaces from a pull request tree when CI passes `--spec`, so a fork PR can submit text the workflow ingests without the agent selecting it; this is a recall-first medium, though the spec copy is normally first-party.
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 step instructs installing this skill via `kendex add vanillagreencom/kendex`, which fetches installed skill material from a repository whose ownership is not established as first-party, so it is a common/reputable unofficial inbound dependency (medium), while the runtime scripts and vendored schema are local-only.
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.