Use when flutter_rust_bridge CI fails on the default branch/main/master, especially to distinguish ordinary CI repair from a regression introduced after a previously green default-branch commit.
68
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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.
This workflow (per SKILL.md) instructs the user/agent to “check the latest relevant run” and “use gh-actions-live-logs” to read GitHub Actions job logs at runtime, which are outsider-authored text (public web/GitHub runtime logs not authored by the operating user) that can include free-form, potentially prompt-injection content.
1d5348b
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.