pincushion-mcp@1.12.0
Visual feedback as agent work packets. Stakeholders drop pins on your live app; your AI coding agent reads each pin (selector, screenshot, DOM, thread, acceptance criteria) via MCP and ships the fix.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiSource supports a guarded, explicit-command agent configuration and skill installation capability, which warrants a warning under the supplied policy. The inspected behavior does not support the scanner's malicious verdict or publication blocking.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
Run the setup subcommand and approve editor connection or critique setup.
Impact
Changes the selected agent's available instructions and connection within the project. The inspected consent gates do not establish authorization for unrestricted future updates.
Mechanism
Writes project-local MCP configuration and publishes package-provided skill files for the selected agent.
AI rationale
Source supports a guarded, explicit-command agent configuration and skill installation capability, which warrants a warning under the supplied policy. The inspected behavior does not support the scanner's malicious verdict or publication blocking.
Evidence
server.jssetup.mjslib/setup-core.jslib/client-critique-install.jslib/claude-critique-install.jslib/setup-runtime.js.codex/config.toml.mcp.json.cursor/mcp.json.vscode/mcp.jsonSKILL.md
Network endpoints1
registry.npmjs.org
Decision evidence
public snapshotAI called this Suspicious at 94.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- server.js activates agent setup through an explicit setup subcommand.
- setup.mjs requires approval before installing the project runtime and connecting the selected editor.
- lib/setup-core.js targets project-local Codex configuration.
- The critique installers create agent skill files with exclusive creation and collision checks.
- setup.mjs asks for additional approval before installing critique assets and saving cloud evidence.
- lib/setup-runtime.js installs dependencies with lifecycle scripts disabled.
Evidence against
- package.json contains no automatic installation lifecycle hooks or runtime self-dependency.
- Inspected setup code preserves inherited settings and rejects unsafe paths and conflicting assets.
- The flagged Maestro download command is printed as installation guidance.
- Inspected login code implements package authentication through a state-checked loopback callback; no credential theft was established.
Behavioral surface
ChildProcessCryptoDynamicRequire
Source & flagged code
12 flaggedmobile-wall.mjsView file
17// injectable so both modes are testable without a simulator.
L18: import { execFileSync } from 'node:child_process';
L19: import {
High
mobile-wall.mjs#virtual:normalized:round1View file
121function publicUrlFrom(text) {
L122: const m = /(https?:\/\/[^\s"'<>]+)/.exec(String(text || ''));\n return m ? m[1].replace(/[),.;]+$/, '') : '';\n}\n\nasync function fetchCloudAnnotations(ctx, { baseUrl, key, proje...
L123: }
Critical
Same File Env Network Execution
A single source file combines environment access, network access, and code or shell execution with blocking evidence.
mobile-wall.mjs#virtual:normalized:round1View on unpkg · L12117// injectable so both modes are testable without a simulator.
L18: import { execFileSync } from "node:child_process";
L19: import {
...
L32: const DEFAULT_OUT = "crit-wall";
L33: const DEFAULT_FUNCTION_BASE = "https://dpsqzszdviltqvethxbr.supabase.co/functions/v1";
L34:
...
L78: function isSignedIn() {
L79: if (process.env.PINCUSHION_LICENSE_KEY) return true;
L80: try { return !!readFileSync(join(homedir(), ".pincushion", "license-key"), "utf8").trim(); } catch { return false; }
L81: }
...
L97: const firstLine = (e) => String(e.message || e).split("\n")[0];
L98: const execErrText = (e) => [e?.stderr, e?.stdout, e?.message].filter(Boolean).join("\n");
Findings
5 Critical8 High4 Medium6 Low
CriticalSame File Env Network Executionmobile-wall.mjs#virtual:normalized:round1
CriticalCredential Exfiltrationserver.js
CriticalDownload Executemobile-wall.mjs#virtual:normalized:round1
CriticalTrigger Reachable Dangerous Capabilityserver.js
CriticalPrevious Version Dangerous Deltalogin.mjs
HighChild Processmobile-wall.mjs
HighShell
HighCommand Output Exfiltrationmobile-wall.mjs#virtual:normalized:round1
HighSandbox Evasion Gated Capabilitylib/setup-runtime.js
HighCopied Package Dependency Bridgelib/posthog.js
HighTrigger Reachable Credential Exfiltrationserver.js
Affected versions and remediation
This report applies to pincushion-mcp@1.12.0.
See all versions of pincushion-mcp for other recorded verdicts.
- Review the evidence and your use of pincushion-mcp@1.12.0 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.