Use when migrating Chromium layout tests to DevTools unit tests or API tests.
68
85%
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
The 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.
SKILL.md instructs the agent to use local copies of a downloaded legacy test file and expectation text, which at runtime likely comes from outsider-authored web/package content rather than the user’s own authored files (indirect injection via reading those downloaded `.js`/`-expected.txt` into the LLM context to rewrite the test).
de3f9ca
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.