Maintain model-routing audit golden fixtures and expected outputs.
72%
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 ./.github/skills/model-routing-golden/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 workflow captures and processes logs and artifacts from GitHub via the local `gh aw logs` tool, which can contain outsider-authored pull request or issue content.
github/gh-aw
2ecfece
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.