huashu-douyin-script
抖音爆款脚本创作工作流。从竞品视频拆解到脚本生成的完整流程：下载抖音视频→Gemini视频分析→爆款公式提炼→脚本+分镜生成→AI味审校。 当用户提到"抖音脚本"、"爆款拆解"、"竞品分析"、"带货脚本"、"千川素材"、"种草脚本"、"视频拆解"、"抖音视频分析"时使用此技能。
72
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Multiple URLs point to direct shell installers or an unverified GitHub repository (raw GitHub install.sh, astral.sh shell installer, and a generic GitHub remote) which are high-risk because they can deliver and execute arbitrary code; the remaining links are to mainstream content or vendor sites and are lower risk.
Low
Low-risk findings.
2 low severity findings. 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
Step 2-3 takes user-provided Douyin links (including short links or “share text”), downloads the corresponding video content, then Step 3 uploads that video plus the constructed free-form prompt to Gemini for analysis—so outsider-authored text/content can flow into the LLM at runtime via the selected video.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The install script fetches remote code at runtime (curl to raw.githubusercontent.com and a git pull from https://github.com/$REPO.git) which would retrieve and install skill code that the agent would then execute or rely on, specifically the URLs https://raw.githubusercontent.com/alchaincyf/Write-Prompt/master/.claude/skills/douyin-viral-script/install.sh and https://github.com/$REPO.git are used in-install to fetch code.
- Repository
- alchaincyf/huashu-skills
- Commit
35e7cf3
- 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.