aimarket-mcp@0.6.4
VERIFIED· install onlyPublisher claims: "alexar76 ecosystem MCP gateway — SSRF-hardened web fetch/search + Metis verify (stdio + HTTP)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 4 of 4 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified 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
AIMARKET_API_KEYConfiguration, not credentials: AIFACTORY_ENV, AIMARKET_HUB_URL, AIMARKET_MCP_HOST, AIMARKET_MCP_KEY, AIMARKET_MCP_PORT, AIMARKET_MCP_PUBLIC, AIMARKET_MCP_RATE, AIMARKET_MCP_TRUSTED_PROXIES, AIMARKET_MCP_VISITOR_SALT, AIMARKET_METIS_KEY, AIMARKET_METIS_URL, AIMARKET_SANDBOX_VISITOR, AIMARKET_SEARCH_URL- Where it talks to
- no vendor host named in the codeAlso modelmarket.dev, duckduckgo.com — 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
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names modelmarket.dev, duckduckgo.com as well as its own vendor. The guard injects AIMARKET_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 0.6.3
vet-skills diff aimarket-mcp 0.6.3 0.6.4In the sandbox, this version reached for nothing 0.6.3 did not. Compared from the two recorded runs, not from source.
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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
"http://[::1]/", "http://localhost/", "file:///etc/passwd", "ftp://x/",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert target == "https://93.184.216.34:8443/x"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert str(seen[0].url) == "https://93.184.216.34:8443/result"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.r = await _rpc(c, "tools/call", {"name": "web_fetch", "arguments": {"url": "http://169.254.169.254/latest/meta-data/"}})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."http://127.0.0.1/", "http://10.0.0.1/", "http://169.254.169.254/",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."http://127.0.0.1/", "http://10.0.0.1/", "http://169.254.169.254/",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert target == "http://93.184.216.34:8080/x" and headers == {} and extensions == {}Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert str(seen[0].url) == "https://93.184.216.34:8443/result"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert target == "http://93.184.216.34/path?q=1", targetFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert target == "http://93.184.216.34/path?q=1", targetFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert target == "http://93.184.216.34:8080/x" and headers == {} and extensions == {}Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.target, headers, extensions = security.pin_target("http://93.184.216.34:8080/x")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.monkeypatch.setattr(tools, "METIS_URL", "https://user:[email protected]:8443/base?key=query-secret")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert target == "https://93.184.216.34:8443/x"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.target, headers, extensions = security.pin_target("http://93.184.216.34:8080/x")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.for url in ("http://localhost:8080/admin", "file:///etc/passwd"):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. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for aimarket-mcp@0.6.4 as of 42 min ago. This is the package itself, not its dependencies.