pincushion-mcp
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.
This report shows the evidence for pincushion-mcp@1.12.5. 0 of 26 known versions are blocked or flagged. See all versions.
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe flagged mobile-wall match is an instructional string, and its capture functionality is exposed through an explicit CLI command. The reviewed credential handling belongs to a provider workflow, while the package discloses product analytics and provides telemetry opt-outs.
Decision evidence
public snapshot- package.json defines start and test scripts, with no install lifecycle hook in the inspected scripts section.
- The mobile-wall feature runs as an explicit CLI subcommand; its capture mode is described as manual.
- The package discloses that PostHog receives product events, not code, pin bodies, URLs, file contents, or email.
- PostHog telemetry has PINCUSHION_NO_TELEMETRY and DO_NOT_TRACK opt-outs.
- The inspected credential upload path accepts a caller-supplied deployment credential as part of a provider workflow.
Source & flagged code
12 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@1.12.5.
The versions list below shows the verdict for each recorded version.
- Review the evidence and your use of pincushion-mcp@1.12.5 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.