Load when implementing an issue or applying review fixes as a dev agent.
71%
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/dev/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 dev-implement and dev-fix workflows read GitHub issue bodies and comments (`gh issue view ... body,comments`) and Linear issue descriptions and comments (`linear.sh issues get` and `comments list`) before acting, and these are tracker text an outsider can post into without the agent selecting an 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 remote locator is the README install command `kendex add vanillagreencom/kendex --skill dev`, an instructed setup path that installs this skill's own material from the author's GitHub repository, so it is a common/reputable unofficial inbound dependency (the author's project, not a recognized first-party vendor), which yields 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.