Install
$ agentstack add skill-mucaktr-challenge-aware-webbridge-challenge-aware-webbridge ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Challenge Aware WebBridge
Overview
Use this skill to keep a browser task moving when a verification page interrupts normal automation. Detect challenge pages, hand control to the user cleanly, wait for the challenge to clear, then resume the original task from the same Kimi WebBridge session.
Workflow
- Reuse one stable
sessionname for the whole user task. Do not split a single browsing task across multiple session names. - After navigation, run
scripts/detect_verification_page.pyif the page title, URL, or visible text looks suspicious. - If no challenge is detected, continue normal browsing.
- If a challenge is detected:
- Tell the user plainly that the site is waiting for manual verification.
- Keep the current tab and session alive.
- Bring the page into view if needed so the user can interact with it.
- If the user explicitly asks for prep, only do non-submitting actions such as opening the page, waiting for layout, or focusing a neutral area outside the challenge.
- Do not claim the skill can bypass, solve, or defeat the challenge automatically.
- Run
scripts/wait_for_clearance.pyto poll until the interstitial is gone or the timeout expires. - When the page clears, take a fresh
snapshotand resume the original task.
Safe Defaults
- Prefer compact
snapshotandevaluateprobes over broad page dumps. - Treat title or URL clues such as
checkLoading,turnstile,captcha,verify, orchecking your browseras strong signals. - Keep all user-facing language calm and concrete. Explain what is blocking the task and what the user should do next.
- Never store secrets, cookies, or personal data in helper scripts or repo files.
- Never present this skill as an anti-bot evasion tool.
Tooling
- Use
scripts/webbridge_request.pyfor daemon calls, especially on Windows where request bodies should be posted from a UTF-8 temp file. - Use
scripts/detect_verification_page.pyto classify the current page as clear or challenged. - Use
scripts/wait_for_clearance.pyafter user handoff to detect when the site is ready again.
References
- Read
references/challenge-patterns.mdfor detection cues and recovery patterns. - Read
references/user-messaging.mdfor short user-facing handoff language.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Mucaktr
- Source: Mucaktr/challenge-aware-webbridge
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.