deep-research
多源深度调研管道（Web Deep Research + Coder 合成 + 云端模型咨询）。 Use when: 技术问题需要多源调查、设计决策需要证据、operator说"调研"/"research"、需要咨询云端模型。 Not for: 简单搜索（直接用 WebSearch）、已有结论的确认。 Output: 调研报告 + 证据合成 或 咨询文档（含回填区）。
68
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt explicitly describes an "API 提取法 (backend-api/conversation/{id} + Bearer token)", which requires including a bearer token in API requests and therefore risks the LLM needing to handle or emit secret token values verbatim.
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:53-69 describes Step 2 “三路并行 Web 调研” pulling content from public web sources (browser automation / artifact extraction) and then Step 3/GPT Pro “读全部四份文档” feeding those outsider-authored web-research reports into the agent/LLM context.
- Repository
- zts212653/clowder-ai
- Commit
80782c5
- 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.