pincushion-mcp@1.11.16
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 2mo ago · by lpm-firewall-aiNo automatic install-time attack or covert credential harvesting was confirmed. Runtime package installation and shell execution remain high-impact capabilities behind explicit commands.
Decision evidence
public snapshot- The snapshot utility can install Playwright packages at runtime and then download Chromium.
- The mobile publish command executes a configurable deployment command through a shell.
- Mobile publishing can upload a selected screenshot with a license-key header to the configured cloud endpoint.
- package.json has no preinstall, install, or postinstall hook.
- The shell and provisioning behavior is reached only through explicit CLI subcommands.
- The analytics helper hashes its distinct identifier before sending it.
Source & flagged code
11 flaggedA single source file combines environment access, network access, and code or shell execution with blocking evidence.
mobile-wall.mjs#virtual:normalized:round1View on unpkg · L121Findings
Affected versions and remediation
This report applies to pincushion-mcp@1.11.16.
See all versions of pincushion-mcp for other recorded verdicts.
- Review the evidence and your use of pincushion-mcp@1.11.16 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.