Update to AnyQR

{
  "description": "Decode and review a QR payload before the user acts on it. Use when the user asks what a QR code does, whether its contents look suspicious, what data it exposes, or for a safety check of an attached QR image or remote QR image URL. Do not use for generic QR education, destination reputation checks, or requests to open or follow encoded links.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 222
    }
  ],
  "name": "qr-payload-safety-review",
  "skill_md_contents": "---\nname: qr-payload-safety-review\ndescription: Decode and review a QR payload before the user acts on it. Use when the user asks what a QR code does, whether its contents look suspicious, what data it exposes, or for a safety check of an attached QR image or remote QR image URL. Do not use for generic QR education, destination reputation checks, or requests to open or follow encoded links.\n---\n\n# QR Payload Safety Review\n\n## Gather the input\n\nRequire an attached QR image, a remote QR image URL, or an already hydrated model-visible QR payload. If none is available, ask the user to provide one.\n\nDo not ask the user to transcribe an encoded payload when the `qr-code` tool can decode the supplied image.\n\n## Decode the QR code\n\n1. Reuse the latest model-visible `qrCodeInformation` when the user clearly refers to the current widget state.\n2. Otherwise call `qr-code` with exactly one source:\n   - `qrCodeFile` for a ChatGPT-hosted image file.\n   - `qrCodeImageUrl` for a remote QR image URL.\n3. Treat returned `structuredContent.qrCodeInformation` as authoritative. Do not infer a payload if decoding fails.\n\n## Review the payload\n\nExplain the behavior implied by `kind` and the exact meaningful fields:\n\n- For `url`, identify the scheme and destination host. Flag plain HTTP, embedded credentials, raw IP addresses, unusual ports, or visually confusing hostnames as potential concerns.\n- For `mailto`, `sms`, and `tel`, identify the recipient and any prefilled content so the user knows what action scanning prepares.\n- For `wifi`, state that the QR contains network access details and indicate whether a password is embedded without repeating that password unnecessarily.\n- For `vcard`, `calendar`, and `geo`, summarize the personal, scheduling, or location information that would be imported or displayed.\n- For `raw`, identify any recognizable scheme conservatively. Treat an unknown scheme as unknown rather than guessing its behavior.\n- For plain `text`, distinguish inert text from instructions that try to persuade the user to take a separate action.\n\nUse calibrated language. Say “no obvious structural warning signs” instead of declaring a payload safe. Distinguish facts present in the payload from interpretation.\n\n## Deliver the review\n\nReturn four concise sections:\n\n1. **What it does** — the action scanning is expected to prepare.\n2. **What it contains** — the relevant decoded fields, with secrets redacted when practical.\n3. **Potential concerns** — only payload-based observations.\n4. **Safer next step** — a concrete way to verify or proceed cautiously.\n\nKeep the decoded widget available so the user can inspect the exact payload.\n\n## Boundaries\n\nDo not open the encoded destination, submit a message, place a call, join a network, or execute a custom scheme. Do not claim malware scanning, domain reputation, ownership verification, or live destination availability; the app exposes none of those capabilities.\n"
}