G.A.I.N 版本历史 - 8 个版本
G.A.I.N 作者: CyberWardion
G.A.I.N 版本历史 - 8 个版本
小心旧版本!显示这些版本是为了测试和参考目的。您应该始终使用附加组件的最新版本。
最新版本
版本 0.5.29
发布于 2026年8月12日 - 739.95 KB适用于 firefox 140.0 及更高版本源代码遵循 保留所有权利 发布
较早版本
版本 0.5.26
发布于 2026年7月16日 - 727.99 KB适用于 firefox 140.0 及更高版本Improved detection precision and stability for G.A.I.N browser protection.
This version reduces false positives around safe examples and public technical references, including documentation placeholders, local/private IP examples, reserved example phone numbers, public blockchain transaction hashes, invalid IBAN examples, and order/ticket-style IDs.
Also includes custom word and regex policy support, policy sync improvements, and additional reliability checks for redaction, blocking, warn, and log-only policy behavior.源代码遵循 保留所有权利 发布
版本 0.5.22
发布于 2026年7月14日 - 725.27 KB适用于 firefox 140.0 及更高版本G.A.I.N. 0.5.22 improves live browser enforcement so redaction follows the policies configured in your dashboard. Mixed prompts now redact only the data types covered by active policies, including API keys, secrets, and database connection strings, while leaving unrelated text unchanged.
Also includes improved regression coverage for crypto seed phrases and mixed sensitive-data prompts.源代码遵循 保留所有权利 发布
版本 0.5.20
发布于 2026年7月8日 - 723.2 KB适用于 firefox 140.0 及更高版本G.A.I.N 0.5.20 improves reliability and performance for AI prompt and file protection:- Reduces per-tab memory work by lazy-loading seed-phrase word data only when needed.
- Caches send-button candidates to avoid repeated full-page queries while scanning.
- Hardens multi-file upload handling so mixed warn/redact/block batches do not bypass warnings.
- Fails closed when PDF/DOCX text extraction fails, blocking unscannable sensitive uploads instead of allowing them silently.
- Adds regression coverage for file-upload, redaction, policy, and network-guard cases.
源代码遵循 保留所有权利 发布
版本 0.5.15
发布于 2026年7月5日 - 431.45 KB适用于 firefox 140.0 及更高版本源代码遵循 保留所有权利 发布
版本 0.5.13
发布于 2026年7月1日 - 312.08 KB适用于 firefox 140.0 及更高版本Initial release of G.A.I.N.
G.A.I.N runs sensitive-data detection locally in your browser on supported AI tools
(ChatGPT, Claude, Gemini, Microsoft Copilot, Perplexity, DeepSeek). When it detects
secrets or personal data in a prompt or an attached text file, it applies your
organization's policy: log, warn, redact on the device, or block before the data is sent.
Only metadata (the AI tool used, detector category, severity, and action) is sent to the
organization dashboard. Prompt text, pasted values, and file contents never leave the device.源代码遵循 保留所有权利 发布
版本 0.5.7
发布于 2026年6月26日 - 285.86 KB适用于 firefox 140.0 及更高版本- Sensitive-data policies now apply per detected item: each type (API keys,
credentials, emails, IBANs, national IDs, etc.) follows its own configured
action — redact, warn, block, or log — instead of one action for the whole
message. - Lower-risk detections now show a lighter, less interruptive warning.
- Detection and reliability improvements.
源代码遵循 保留所有权利 发布
- Sensitive-data policies now apply per detected item: each type (API keys,
版本 0.5.4
发布于 2026年6月18日 - 281.7 KB适用于 firefox 140.0 及更高版本G.A.I.N 0.5.4 adds improved organization onboarding, department selection during setup, live device presence, managed deployment support, and stronger local redaction behavior across supported AI tools.
This version also improves policy sync, uninstall handling, and metadata-only reporting for team deployments.源代码遵循 保留所有权利 发布