vulnerability-exposure-mcp@1.2.1
CAUTION· not startedPublisher claims: "MCP server that checks IPs, domains, CVEs and software versions for confirmed vulnerabilities and exposure" 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
ABUSEIPDB_API_KEYGREYNOISE_API_KEYNVD_API_KEYSHODAN_API_KEYVIRUSTOTAL_API_KEYVT_API_KEYConfiguration, not credentials: VULN_EXPOSURE_CACHE, VULN_EXPOSURE_CACHE_DIR, VULN_EXPOSURE_LOG_LEVEL, VULN_EXPOSURE_QUOTA_PER_HOUR, VULN_EXPOSURE_WATCHLIST- Where it talks to
- no vendor host named in the codeAlso nist.gov, cisa.gov, first.org, osv.dev, shodan.io, greynoise.io, spamhaus.org, crt.sh, sans.edu, certspotter.com, virustotal.com, abuseipdb.com, mitre.org, endoflife.date — 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 nist.gov, cisa.gov, first.org, osv.dev, shodan.io, greynoise.io, spamhaus.org, crt.sh, sans.edu, certspotter.com, virustotal.com, abuseipdb.com, mitre.org, endoflife.date as well as its own vendor. The guard injects ABUSEIPDB_API_KEY, GREYNOISE_API_KEY, NVD_API_KEY, SHODAN_API_KEY, VIRUSTOTAL_API_KEY, VT_API_KEY only into requests to the host you bind (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.
What changed since 1.1.0
vet-skills diff vulnerability-exposure-mcp 1.1.0 1.2.1This version reaches for something 1.1.0 did not: 14 new hosts (abuseipdb.com, certspotter.com, cisa.gov, crt.sh, …) · 6 new credential variables (ABUSEIPDB_API_KEY, GREYNOISE_API_KEY, NVD_API_KEY, SHODAN_API_KEY, …). Compared from the two recorded runs, not from source.
- New hosts
- abuseipdb.com, certspotter.com, cisa.gov, crt.sh, endoflife.date, first.org, greynoise.io, mitre.org, nist.gov, osv.dev, sans.edu, shodan.io +2
- New credential variables
- ABUSEIPDB_API_KEY, GREYNOISE_API_KEY, NVD_API_KEY, SHODAN_API_KEY, VIRUSTOTAL_API_KEY, VT_API_KEY
1.1.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Image alt text carrying instructions; 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
@pytest.mark.parametrize("location", ["http://other.example/", "https://169.254.169.254/latest", "https://[::1]/",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Claude running "Run a security assessment of PHP 8.3.10" with this server: 7 tool calls, a report that passed check_report, an executive summary and a key findiFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."file:///etc/passwd"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# *sbom*.json). Anything else is refused, so a mistyped path can't send another file's lines anywhere.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.ENDOFLIFE_URL = "https://endoflife.date/api/v1/products"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."source": "endoflife.date (https://endoflife.date/windows)",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.stripped = text.lstrip(" \t\r\n")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.("https://169.254.169.254/latest", "private address"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 vulnerability-exposure-mcp@1.2.1 as of 22 min ago. This is the package itself, not its dependencies.
What would make this Verified
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim mrfrazer25: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- 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.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.