Daily maintainer routine — open issues / PR review / build health / broken-link audit via canonical MAINTAINER-PIPELINE. TRIGGER when: user says "maintainer", "跑 maintainer", "daily PR review", "issue triage", or routine `twmd-maintainer-daily` fires.
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.
SKILL.md Stage 1/2 的運行工作流會透過 `gh issue list`/`gh pr list`/`gh issue view N --json comments -q '.comments[-1]'` 讀取 GitHub 上由外部作者撰寫的 issue/PR 與評論自由文本(在未選中特定來源前由列表與“last comment”邏輯直接 ingest)。
4d66426
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.