Load for any Linear read or write: issues, projects, cycles, milestones, initiatives, labels.
76%
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/linear/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 reads Linear issue descriptions and comment bodies (`issues list`, `issues get`, `issues bulk-get`, `comments list`/`bulk-list`, `attachments list`) from the Linear tracker, which outsiders can write into through Linear intake, GitHub sync, and comments, so the agent ingests that text without first 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 only inbound source is the README setup command `kendex add vanillagreencom/kendex --skill linear`, which installs this skill from a GitHub repository owned by an individual author, so it is an unofficial, reputable-looking dependency and the tier is 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.