vdb-mcp@0.2.9
CAUTION· not startedPublisher claims: "MCP server for VDB — AI-aware vulnerability database (packages, MCP servers, models). Check packages for CVEs and slopsquatting before installing." 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
VDB_API_KEYVDB_API_TOKENVDB_PROXY_TOKENConfiguration, not credentials: MCP_MODE, MCP_PORT, UPSTREAM, VDB_API_ADDR, VDB_API_URL, VDB_CLIENT, VDB_GIT_SHA, VDB_HARDEN_TIMEOUT, VDB_LOG_LEVEL- Where it talks to
- no vendor host named in the codeAlso ai.kr — 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 ai.kr as well as its own vendor. The guard injects VDB_API_KEY, VDB_API_TOKEN, VDB_PROXY_TOKEN 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 0.2.8
vet-skills diff vdb-mcp 0.2.8 0.2.9This version reaches for something 0.2.8 did not: 1 new credential variable (VDB_PROXY_TOKEN). Compared from the two recorded runs, not from source.
- New credential variables
- VDB_PROXY_TOKEN
0.2.8 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 2026-11-20 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call detected; Credential pass-through configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
# docker run -i --rm \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."https://203.0.113.7/v1/auth/me"]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert [c[1] for c in calls[1:]] == ["https://203.0.113.7/v1/auth/me",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert [c[1] for c in calls[1:]] == ["https://203.0.113.7/v1/auth/me",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert "subprocess.run(body" not in json.dumps(body)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert calls[1][1] == "https://203.0.113.7:8443/api/v1/auth/me"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls." subprocess.run(body, shell=True)\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# os.system(cmd), eval(expr), pickle.loads(blob) with a tainted argument allFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.assert calls[1][1] == "https://203.0.113.7:8443/api/v1/auth/me"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."https://203.0.113.7/v1/auth/me"]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.# request and forwards it to the API — only together with the proxy secret,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# the API only with the proxy secret (see _headers).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# has no summary to chase — `subprocess.run(cmd)` in the user's handler — andFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."https://203.0.113.8/v1/auth/me"]Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."https://203.0.113.8/v1/auth/me"]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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim 0pstech: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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 using a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.