TheBotique

overwing

Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person, identify any User-Agent string against Overwing Atlas, a registry of AI crawlers, fetchers and browser agents with verification classes (no key

as observed 2026-10-02T07:46:18.975Z
Identifier
overwing
Source
ClawHub
Version observed
1.8.0
Source repository
not published
Repository observation
No source repository listed
First observed here
2026-09-25T00:46:42.104Z
Observations recorded
5
Installs (reported upstream)
3
Weekly downloads (upstream)
413
Declared license
MIT-0

Observation history

2026-10-02T07:46:18.975Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "Overwing Beacon: beacon sample, start, report" "overwing 1.8.0\n\n- Added support for passwordless account signup directly from the CLI, requiring no email or password.\n- Increased daily check limit for passwordless accounts t
latestVersion "1.6.0" "1.8.0"
2026-10-01T06:47:50.210Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "evaluate works with no key: 10 checks a day, inputs up to 2,000 characters, text not stored. New Languages section: text can be in any language, tested in nine besides English. te "Overwing Beacon: beacon sample, start, report"
latestVersion "1.4.0" "1.6.0"
summary "Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person, identify any User-Agent "Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person, identify any User-Agent
2026-09-29T04:47:03.526Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "Atlas: identify any User-Agent string (who), search the agent registry (agents), public summary (atlas)" "evaluate works with no key: 10 checks a day, inputs up to 2,000 characters, text not stored. New Languages section: text can be in any language, tested in nine besides English. te
latestVersion "1.2.0" "1.4.0"
summary "Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person, and identify any User-A "Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person, identify any User-Agent
2026-09-26T01:46:07.395Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "recommended_action, --context option, outbound-message rule set" "Atlas: identify any User-Agent string (who), search the agent registry (agents), public summary (atlas)"
latestVersion "1.1.0" "1.2.0"
summary "Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person. One API call returns a "Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person, and identify any User-A

Correction

If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.