sales-cs-review
当用户想复盘或升级已启用的 sales-cs 时使用。扫描 sales-cs 的 feedback/ 聚合客户 反馈，结合用户意见提出升级建议（调整 MEMORY 客服手册 / 话术 / IDENTITY 称呼 / DECLARED_SKILLS 等），确认后由 main agent 直接改 sales-cs workspace 文件。 sales-cs 是对外 crew，不自行升级，所有调整经本技能由 main agent 落地。
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.
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 的 Step 1/2 会运行 `scripts/scan_feedback.py` 读取 `~/.openclaw/workspace-sales-cs/feedback/*.md` 并把文件内容“read_text”后提取条目/关键词摘要（JSON stdout），随后 Step 2 将“反馈摘要 + 用户本轮诉求”喂给主 LLM；这些 `feedback/*.md` 属于非由运行用户直接选择引入的历史客户反馈文档，因此属于“outsider-authored free text（客户反馈/第三方内容）经运行时本地文件读取→通过 stdout JSON 被注入模型上下文”的间接提示注入风险。
- Repository
- TeamWiseFlow/xiaobei
- Commit
bcef823
- 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.