registry / @sapiom/mcp / 0.12.8
@sapiom/mcp@0.12.8
Local Sapiom developer MCP server (sapiom-dev) — the unmetered surface for building and operating on Sapiom; today it scaffolds, tests, deploys, and inspects orchestrations. Not the remote Sapiom capability MCP.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe reverse-shell finding is a false positive: child_process is limited to opening the user-facing OAuth browser URL, while the callback is loopback-only and state-validated. Remote instruction and analytics behavior are vendor-aligned runtime features, not a concrete malicious chain.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
User runs sapiom-mcp or configures and starts this MCP server.
Impact
No confirmed unauthorized execution, exfiltration, destructive action, or AI-agent control-surface mutation.
Mechanism
stdio MCP developer tooling with OAuth and Sapiom API calls
AI rationale
The reverse-shell finding is a false positive: child_process is limited to opening the user-facing OAuth browser URL, while the callback is loopback-only and state-validated. Remote instruction and analytics behavior are vendor-aligned runtime features, not a concrete malicious chain.
Evidence
package.jsondist/index.jsdist/auth.jsdist/credentials.jsdist/instructions-fetch.jsdist/register-tool.jsdist/tools/authenticate.jsdist/tools/sandbox.js~/.sapiom/credentials.json
Network endpoints2
api.sapiom.aiapi.sapiom.dev
Decision evidence
public snapshotAI called this Clean at 95.0% confidence as Benign with medium false-positive risk.
Evidence for AI clean decision
- No npm lifecycle hook is declared; the manifest only exposes the MCP bin and development scripts.
- The flagged child-process code only launches the OAuth URL with platform browser openers.
- OAuth uses a loopback callback and validates a random state before token exchange.
- Credential storage is limited to ~/.sapiom/credentials.json with restrictive write permissions.
- Remote instructions are fetched from the configured Sapiom API and have a bundled offline fallback; no static malicious payload is present.
Evidence against
- Starting the MCP server fetches remotely changeable instruction text that capable clients may surface to a model.
- Tool-call analytics captures supplied tool arguments for the vendor telemetry pipeline.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
5 flaggeddist/auth.jsView file
1import * as http from "node:http";
L2: import * as crypto from "node:crypto";
L3: import { spawn } from "node:child_process";
L4: import { URL, URLSearchParams } from "node:url";
L5: /**
...
L9: * - NEVER a visible console. The previous `execSync('start "" "<url>"')`
L10: * spawned cmd.exe, which pops a console window on the user's screen when
L11: * the caller isn't attached to one (an MCP server child of a GUI app
...
L16: * a cmd.exe command line treats as a command separator unless quoted
L17: * exactly right. The PowerShell command is passed BASE64-ENCODED
L18: * (-EncodedCommand), so no shell ever tokenizes the URL; the
...
L21: *
Critical
Reverse Shell
Source matches reverse-shell style process and socket wiring.
dist/auth.jsView on unpkg · L11Trigger-reachable chain: manifest.exports -> dist/auth-api.js -> dist/auth.js
L1: import * as http from "node:http";
L2: import * as crypto from "node:crypto";
L3: import { spawn } from "node:child_process";
L4: import { URL, URLSearchParams } from "node:url";
L5: /**
...
L9: * - NEVER a visible console. The previous `execSync('start "" "<url>"')`
L10: * spawned cmd.exe, which pops a console window on the user's screen when
L11: * the caller isn't attached to one (an MCP server child of a GUI app
...
L16: * a cmd.exe command line treats as a command separator unless quoted
L17: * exactly right. The PowerShell command is passed BASE64-ENCODED
L18: * (-EncodedCommand), so no shell ever tokenizes the URL; the
...
L21: *
Critical
Trigger Reachable Dangerous Capability
A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior.
Findings
2 Critical3 High3 Medium4 Low
CriticalReverse Shelldist/auth.js
CriticalTrigger Reachable Dangerous Capabilitydist/auth.js
HighChild Processdist/auth.js
HighShelldist/auth.js
HighSandbox Evasion Gated Capabilitydist/auth.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @sapiom/mcp@0.12.8.
See all versions of @sapiom/mcp for other recorded verdicts.
- Review the evidence and your use of @sapiom/mcp@0.12.8 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.