Find flaky and repeatedly failing tests from recent CI history and file a ticket for each one, before people learn to ignore them.
73
92%
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.
The required workflow reads CI run logs via `gh run view`, which can contain outsider-authored test failure messages and console output.
GitHub CI run logs (gh run view --log-failed)
content-type · 1 site
The workflow instructs the agent to fetch and act on CI run logs via `gh run view <id> --log-failed`; these logs contain test failure messages and console output that can be authored or influenced by third parties (contributors, test authors, or anyone who can push code or open PRs), creating an indirect prompt-injection surface.
SKILL.md
28
read failed job logs with `gh run view <id> --log-failed`.