Scan the merged pull requests since the last changelog entry and draft the next one, then open a pull request with the draft.
75
94%
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 workflow reads pull request titles, bodies, and labels from GitHub or GitLab, which are authored by outside contributors.
github.com
domain · 5 sites
The plugin uses the `gh` CLI to fetch pull request titles, bodies, and labels from GitHub, which are authored by outside contributors and could contain prompt-injection content.
SKILL.md
18
The hosting platform's CLI (`gh` for GitHub, `glab` for GitLab) authenticated
SKILL.md
27
for GitHub) and use that date.
SKILL.md
32
- GitHub: `gh pr list --state open --search "docs: draft changelog" --json number,url
SKILL.md
37
- GitHub: `gh pr list --state merged --search "merged:>=<cutoff-date>" --json number,title,body,labels,mergedAt
SKILL.md
48
- GitHub: `gh pr create --title "docs: draft changelog" --body "<summary>"
gitlab.com
domain · 3 sites
The plugin uses the `glab` CLI to fetch merge request titles, bodies, and labels from GitLab, which are authored by outside contributors and could contain prompt-injection content.
SKILL.md
18
The hosting platform's CLI (`gh` for GitHub, `glab` for GitLab) authenticated
SKILL.md
38
- GitLab: `glab mr list --merged --json
SKILL.md
49
- GitLab: `glab mr create --title "docs: draft changelog" --description "<summary>"