po-mcp@0.0.0-alpha.127
CAUTION· not startedPublisher claims: "Domain-aware MCP server selection and access boundaries for Pi sessions composed with Po." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry npm (MCP server)Publisher agimon-ai · publishing for 253 daysInstalls 30,585Last detonated 6d ago
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
MCP_AUTHORIZATION_API_PATH- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- 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. It asks for MCP_AUTHORIZATION_API_PATH and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
$vet-skills run --net declared -- npx -y @agimon-ai/po-mcp
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 2026-11-08 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: Access to sensitive file paths; Prompting user to enter sensitive credentials; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 49 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
48sprocessdependency install exit 1 · (Use `node --trace-warnings ...` to show where the warning was created) npm error Cannot read properties of null (reading 'edgesOut') npm error A complete log of this run can be found in: /tmp/ks-detonate-oYR2IQ/task/home/.npm/_logs/2026-11-08T21_32_33_792Z-debug-0.log
48sclaimednot started: dependency install failed (exit 1); the server itself was not observed
48sprocessscript backend runs setup only
48sprocessno install scripts to re-run
Static findings
HIGH
Access to sensitive file pathsdist/mcpServerConfig-CXaIllri.mjs:1152 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05...env ? { env } : {}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
MCP server using network transport (SSE/HTTP)dist/extensions/server.cjs:1938 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04if (value?.kind === "bearer" && require_mcpServerConfig.isSecretValue(value.token)) return { Authorization: `Bearer ${value.token}` };Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.MEDIUM
MCP server using network transport (SSE/HTTP)dist/extensions/server.cjs:3145 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04if (!require_mcpServerConfig.isSecretName(name) || !require_mcpServerConfig.isSecretValue(value)) throw new require_mcpServerConfig.McpSecretSupplyError(400, "Enter the secret as one line.");Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.MEDIUM
MCP server using network transport (SSE/HTTP)dist/extensions/server.cjs:1939 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04…1,64}$/u.test(value.name) && !RESERVED.has(value.name.toLowerCase()) && require_mcpServerConfig.isSecretValue(value.value)) return { [value.name]: value.value }; throw new Error("…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.MEDIUM
MCP server using network transport (SSE/HTTP)dist/extensions/server.mjs:3623 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04function createMcpServerRuntime(environment = {}, workspaceRoot, getResolver, publishFile, assertPackageActive, getVault, getFs, globalSettings) {Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.MEDIUM
MCP server using network transport (SSE/HTTP)dist/extensions/server.cjs:3634 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04function createMcpServerRuntime(environment = {}, workspaceRoot, getResolver, publishFile, assertPackageActive, getVault, getFs, globalSettings) {Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.MEDIUM
MCP server using network transport (SSE/HTTP)dist/extensions/server.mjs:5 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04…olApproval, Y as isDestructiveMcpTool, _ as MCP_REPOSITORY_ID_QUERY, a as mutateMcpServer, c as handleSettings, d as json$1, f as serverNameOf, g as MCP_FLOW_ID_PARAM, h as routes, i as mcpServerRevision, l as isRecord, n as listManagedMcp…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.MEDIUM
MCP server using network transport (SSE/HTTP)dist/mcpServerConfig-CXaIllri.mjs:1280 · MCP server using network transport (SSE/HTTP) — data sent over network
AST04…arams as K, createSecretResolver as L, REMOTE_MCP_TIMEOUT_MS as M, connectRemoteMcpServers as N, PO_MCP_REMOTE_SERVERS_CONTRACT as O, isUnauthorized as P, isSecretName$1 as R, MCP_SESSION_TOOL_NAME_QUERY as S, formatMcpSessionAuthStatus as…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.CRITICAL
Prompting user to enter sensitive credentialsdist/extensions/server.cjs:3145 · Prompting user to enter sensitive credentials — social engineering
AST03if (!require_mcpServerConfig.isSecretName(name) || !require_mcpServerConfig.isSecretValue(value)) throw new require_mcpServerConfig.McpSecretSupplyError(400, "Enter the secret as one line.");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.HIGH
Access to sensitive file pathsdist/mcpServerConfig-DNTdLi70.cjs:1152 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05...env ? { env } : {}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.CRITICAL
Prompting user to enter sensitive credentialsdist/extensions/server.mjs:3134 · Prompting user to enter sensitive credentials — social engineering
AST03if (!isSecretName(name) || !isSecretValue(value)) throw new McpSecretSupplyError(400, "Enter the secret as one line.");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Instructions loaded
≈3,243 tok
2 files · 36 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0
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 @agimon-ai/po-mcp@0.0.0-alpha.127 as of 6d 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%- 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 agimon-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim agimon-aiPropose a patch to the maintainer