breezing
Team execution mode — backward-compatible alias for harness-work with team orchestration. Composer/composer 2.5 maps to the cursor backend.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
SKILL.md の Phase D Integrated Review Gate で、リモートに読み取り可能な差分対象として `{base_ref}..HEAD`（または `--no-commit` 時は working tree/untracked 変更）を `harness-review` および `codex-companion.sh review` に渡してレビューしており、差分に含まれる outsider-authored 自由文（ユーザーがコミット/追加した内容）がそのままLLM入力になる可能性があります。
- Repository
- Chachamaru127/claude-code-harness
- Commit
7d8deba
- Audited
- Security analysis
Is this your skill?
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.