Investigate an Oxc bug report through triagebot-action's reproduce, diagnose, verify, or fix stage using the affected subsystem's compatibility contract and tests.
80%
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/triage/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 reproduce stage reads the body and all comments of an outsider-authored GitHub issue (reproduce.md:8-9), and the diagnose, verify, and fix stages then consume that report, so reporter-controlled text reaches the agent without it selecting any specific item.
oxc-project/oxc
bdbed9e
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.