keywordgraph-mcp-server@1.9.8
CAUTION· install onlyPublisher claims: "KeywordGraph MCP server - A Model Context Protocol server for network thinking and graph analysis" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- 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: 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
INFRANODUS_API_KEYJWT_SECRETKEYWORDGRAPH_API_KEYMCP_SIGNIN_LOG_SECRETConfiguration, not credentials: BRAND, CORS_ORIGIN, FLY_APP_NAME, INFRANODUS_DELETE, INFRANODUS_FEEDBACK, INFRANODUS_LEARNINGS, MCP_SOURCE, MCPCAT_ANONYMOUS, OPENAI_APPS_CHALLENGE, OPENAI_PATH- Where it talks to
- keywordgraph.com (its own)Also infranodus.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- 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 infranodus.com as well as its own vendor. The guard injects INFRANODUS_API_KEY, JWT_SECRET, KEYWORDGRAPH_API_KEY, MCP_SIGNIN_LOG_SECRET only into requests to keywordgraph.com (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 1.9.5
vet-skills diff keywordgraph-mcp-server 1.9.5 1.9.8This version reaches for something 1.9.5 did not: 1 new credential variable (MCP_SIGNIN_LOG_SECRET). Compared from the two recorded runs, not from source.
- New credential variables
- MCP_SIGNIN_LOG_SECRET
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
- Can be used in ChatGPT Deep Research mode via Developer Mode > ConnectorsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."build": "npx @smithery/cli build",Fix: Pin versions and sources; vendor anything fetched at install time.- Can be used in ChatGPT Deep Research mode via Developer Mode > ConnectorsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.// Bakes in BRAND so `npx infranodus-mcp-server` runs as InfraNodus withoutFix: Pin versions and sources; vendor anything fetched at install time.- Compatible with ChatGPT Deep Research mode via Developer Mode > ConnectorsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.// STDIO/npx mode: resolve identity from the API keyFix: Pin versions and sources; vendor anything fetched at install time."dev": "npx @smithery/cli dev",Fix: Pin versions and sources; vendor anything fetched at install time.<input type="password" id="api_key" name="api_key" required placeholder="Enter your API key">Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(`[MCP:auto-init] Sending synthetic "${method}" request`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(`[MCP] Handling POST / as MCP request`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(`[SSE] POST /message for session ${sessionId}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.- Compatible with ChatGPT Deep Research mode via Developer Mode > ConnectorsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.console.log(` - OAuth token: POST http://localhost:${PORT}/oauth/token`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim keywordgraph: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- 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.