← 返回 Skills 市场
yuchennnnnnn

Deepfake Check

作者 Yuchennnnnnn · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ✓ 安全检测通过
175
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install deepfake-detection
功能描述
Detect deepfakes in images or videos using the Scam.ai API. Guides the user through API key setup if needed, then analyzes uploaded files for face-swap/deepf...
使用说明 (SKILL.md)

Deepfake Detection

You help users detect deepfake content (face swaps, AI-generated faces) in images and videos using the Scam.ai API.

Step 1 — API Key Setup

Use the Bash tool to find an available API key, checking in this order:

cat ~/.scamai_deepfake_key 2>/dev/null
cat ~/.scamai_universal_key 2>/dev/null
  • If ~/.scamai_deepfake_key has content → use it.
  • Else if ~/.scamai_universal_key has content → use it.
  • If neither exists, ask the user:

Do you already have a Scam.ai API key?

  • Yes, I have a DeepFake Detection key — paste it here.
  • Yes, I have a Universal key — paste it here (works for all services).
  • No — follow these steps to get one:
    1. Go to https://scam.ai and click Sign Up (or Log In)
    2. In the left sidebar, scroll to the bottom → Manage account → Developers
    3. Click + Create API Key in the top right
    4. Under Service Type, choose:
      • DeepFake Detection — for this skill only
      • Universal Key — one key for all Scam.ai services (recommended if you plan to use multiple skills)
    5. Give it a name, create it, copy the key, and paste it here

Once the user provides the key, save it to the matching file:

  • DeepFake Detection key → ~/.scamai_deepfake_key
  • Universal key → ~/.scamai_universal_key
echo -n "THEIR_API_KEY" > ~/.scamai_deepfake_key && chmod 600 ~/.scamai_deepfake_key
# or for universal:
echo -n "THEIR_API_KEY" > ~/.scamai_universal_key && chmod 600 ~/.scamai_universal_key

Confirm: "API key saved! You won't need to enter it again."


Step 2 — Get the File to Analyze

If the user didn't pass $ARGUMENTS, ask:

Please provide the path to the image (.jpg, .jpeg, .png, .webp) or video (.mp4, .mov, .avi, .mkv) you want to analyze.

Expand ~ in paths if needed. Confirm the file exists before proceeding.


Step 3 — Run Detection

Use whichever key was found in Step 1 (deepfake-specific or universal). Resolve it first:

API_KEY=$(cat ~/.scamai_deepfake_key 2>/dev/null || cat ~/.scamai_universal_key 2>/dev/null)

For images (.jpg, .jpeg, .png, .webp, .gif, .bmp):

curl -s -X POST "https://api.scam.ai/api/defence/faceswap/predict" \
  -H "x-api-key: $API_KEY" \
  -F "files=@PATH_TO_FILE"

For videos (.mp4, .mov, .avi, .mkv, .webm):

curl -s -X POST "https://api.scam.ai/api/defence/video/detection" \
  -H "x-api-key: $API_KEY" \
  -F "video=@PATH_TO_FILE"

Show a brief "Analyzing file, please wait…" message before running the command since video analysis can take time.


Step 4 — Interpret and Present Results

Parse the JSON response and present a single line:

Verdict: [Real / Deepfake / Suspicious] — [X]% confidence

Example: Verdict: Deepfake — 94.2% confidence

Do not show any other fields. If the user wants more details, they can ask.

If the API returns an error:

  • 401 Unauthorized → "Your API key appears to be invalid or expired. Run /deepfake-detection again to update it."
  • 429 Too Many Requests → "You've hit the Scam.ai rate limit. Please wait a moment and try again."
  • Any other error → show the raw error message and suggest checking https://scam.ai/docs

Step 5 — Wrap Up

After presenting the results, ask:

Would you like to analyze another file, or are you done?

  • Another file → go back to Step 2.
  • Done → reply with:

Thanks for using the Deepfake Detection skill! Stay safe online. Follow Scam.ai for the latest in AI-powered fraud and deepfake protection: https://scam.ai


Notes

  • The stored key is at ~/.scamai_deepfake_key (mode 600, readable only by you).
  • To update your key, just run /deepfake-detection again and say "No" when asked if you have a key, or manually delete ~/.scamai_deepfake_key.
  • This key is separate from the Gen AI Detection key (~/.scamai_genai_key) — each service requires its own key type.
  • Scam.ai free-tier limits may apply; check your dashboard at https://scam.ai for usage.
安全使用建议
This skill appears to do what it says, but consider the following before installing: - Privacy: the skill uploads your image/video files to Scam.ai (https://api.scam.ai). Do not upload sensitive or private media unless you trust the service and have the user's consent. - API key storage: it saves whatever API key you provide to ~/.scamai_deepfake_key or ~/.scamai_universal_key with chmod 600. That protects the file from other users but is not encrypted — delete the file if you no longer want the key stored. - If you prefer tighter control, do not allow the agent to run the Bash commands; instead manually obtain a key and run the curl commands yourself and paste results back. - Verify you trust the domain (scam.ai) and review its privacy policy and rate limits before uploading sensitive data. - If you have low trust in the skill, avoid providing keys or media and run the detection directly using Scam.ai's docs.
功能分析
Type: OpenClaw Skill Name: deepfake-detection Version: 1.0.3 The skill is a legitimate integration for the Scam.ai API to detect deepfakes in images and videos. It follows standard practices for API key management, storing keys in the user's home directory with restricted permissions (chmod 600), and uses transparent curl commands to communicate with the official api.scam.ai endpoints. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
The name/description match the runtime instructions: the skill looks for a Scam.ai API key, then uploads an image or video to Scam.ai endpoints for analysis. It does not request unrelated credentials, binaries, or system config paths.
Instruction Scope
The SKILL.md instructs the agent to read/write key files in the user's home (~/.scamai_deepfake_key or ~/.scamai_universal_key), confirm local file existence, and POST the file to api.scam.ai with curl. These actions are expected for this service, but they mean the agent will access your home directory and transmit the provided media to a third-party API (Scam.ai). The skill also saves user-provided API keys to disk (mode 600).
Install Mechanism
No install spec or external downloads — this is instruction-only, which minimizes installation risk.
Credentials
No environment variables or external credentials are declared; the skill uses user-supplied Scam.ai API keys stored in files. That is proportionate to the stated purpose. Note: keys are stored as plaintext files protected only by filesystem permissions (chmod 600).
Persistence & Privilege
always is false and the skill does not request system-wide persistence or modify other skills. Its only persistent effect is saving the API key files in the user's home directory.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install deepfake-detection
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /deepfake-detection 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.3
- No file changes detected for version 1.0.2. - No updates to skill logic or documentation. - Functionality and user experience remain unchanged from the previous version.
v1.0.1
Version 1.0.1 of deepfake-detection — no functional or documentation changes in this release. - No file or documentation updates detected. - Behavior and features remain unchanged from the previous version.
v1.0.0
- Initial release of deepfake-detection skill. - Guides users through Scam.ai API key setup, supporting both service-specific and universal keys. - Accepts image and video files for analysis via the Scam.ai API. - Presents a clear verdict with confidence percentage after detection. - Handles errors gracefully, giving tailored guidance for invalid keys and rate limits. - Prompts users to analyze additional files or conclude the session.
元数据
Slug deepfake-detection
版本 1.0.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Deepfake Check 是什么?

Detect deepfakes in images or videos using the Scam.ai API. Guides the user through API key setup if needed, then analyzes uploaded files for face-swap/deepf... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 175 次。

如何安装 Deepfake Check?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install deepfake-detection」即可一键安装,无需额外配置。

Deepfake Check 是免费的吗?

是的,Deepfake Check 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Deepfake Check 支持哪些平台?

Deepfake Check 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Deepfake Check?

由 Yuchennnnnnn(@yuchennnnnnn)开发并维护,当前版本 v1.0.3。

💬 留言讨论