pincushion-mcp@1.11.29
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 confirms consent-gated agent configuration and skill installation, which the review policy classifies as a warning. No unconsented install-hook mutation or concrete malicious execution chain was established.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
Run the setup subcommand, select an editor, and approve runtime connection and critique setup.
Impact
Future agent sessions can discover and use the installed Pincushion integration. The inspected flow does not establish consent to unrestricted automatic updates.
Mechanism
The wizard writes a Pincushion MCP entry and installs skill files, with consent, path checks and collision guards.
AI rationale
Source confirms consent-gated agent configuration and skill installation, which the review policy classifies as a warning. No unconsented install-hook mutation or concrete malicious execution chain was established.
Evidence
server.jssetup.mjslib/setup-core.jslib/client-critique-install.jslib/claude-critique-install.jslib/setup-runtime.js.mcp.json.cursor/mcp.json.vscode/mcp.json.codex/config.toml
Network endpoints1
registry.npmjs.org
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The explicit setup subcommand activates the editor integration wizard.
- Setup asks permission before installing the runtime and connecting the selected editor.
- The configuration writer adds a Pincushion MCP entry to project-local editor configuration.
- After another approval prompt, installers create agent skill files using exclusive writes.
- Runtime dependency installation disables lifecycle scripts and uses the npm registry.
Evidence against
- package.json has no automatic npm installation lifecycle hooks or runtime self-dependency.
- The inspected setup preserves conflicting assets and rejects unsafe paths.
- The mobile tool prints Maestro installation instructions; those strings do not establish automatic remote code execution.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStrings
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 Deltascripts/build-mcpb.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@1.11.29.
See all versions of pincushion-mcp for other recorded verdicts.
- Review the evidence and your use of pincushion-mcp@1.11.29 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.