Directory / server

ai.trustysquire/trusty-squire

This directory entry reports an automated security scan of ai.trustysquire/trusty-squire, scanned 2026-07-28. Trust grade A rates provenance, transport, known vulnerabilities and instruction integrity; capability risk is reported separately, not folded into the grade.

registry.modelcontextprotocol.io, scanned 2026-07-28, tool surface via package-source

A 100/100 permalink

Automated checks

Status	Check	Policy	Result
PASS	Listed on the official MCP registry	§1.1	Listed on registry.modelcontextprotocol.io as ai.trustysquire/trusty-squire. 1 finding Registry entry: ai.trustysquire/trusty-squire ↗
PASS	Source repository is public and maintained	§1.2	Active repository with a license. 5 findings Repository ↗ Last push: 0 days ago Stars: 3 License: MIT Security policy (SECURITY.md): absent
PASS	Published package is consistent and attested	§1.3	Package is consistent with its source and carries provenance attestation. 6 findings Package: @trusty-squire/mcp@1.1.4 ↗ Ecosystem: npm Age: 73 days Weekly downloads: 2535 Repo field matches source repo: true Build-provenance attestation: present
PASS	Tool surface is inspectable and proportionate	§2.1–§2.4	Package source scanned. Capabilities detected: filesystem, process-execution, network-egress, credential-access. Reported as capability risk (§2.4); whether each is essential to the server's stated purpose is §2.3 and remains a manual judgement. 25 findings filesystem (filesystem write/delete): dist/install/agents.js filesystem (fs module import): dist/install/agents.js process-execution (child process execution): dist/bot/browser.js process-execution (child process module import): dist/bot/browser.js process-execution (dynamic code evaluation): dist/bot/browser.js filesystem (filesystem write/delete): dist/bot/browser.js filesystem (fs module import): dist/bot/browser.js network-egress (outbound network calls): dist/bot/browser.js filesystem (fs module import): dist/install/cli.js process-execution (child process execution): dist/skill-cli/cli.js process-execution (child process module import): dist/skill-cli/cli.js filesystem (fs module import): dist/skill-cli/cli.js process-execution (child process module import): dist/bot/google-login.js filesystem (fs module import): dist/bot/google-login.js filesystem (fs module import): dist/bot/login-state.js process-execution (child process module import): dist/bot/onboarding-capture.js filesystem (filesystem write/delete): dist/bot/onboarding-capture.js filesystem (fs module import): dist/bot/onboarding-capture.js filesystem (fs module import): dist/operator-env.js credential-access (credential/env access): dist/operator-env.js filesystem (fs module import): dist/bot/operator-recipe.js filesystem (fs module import): dist/bot/profile.js process-execution (child process module import): dist/bot/xvfb.js filesystem (fs module import): dist/bot/xvfb.js Detected capabilities: filesystem, process-execution, network-egress, credential-access
INFO	Transport & authentication	§3	Local (stdio) server: runs with host-process privileges by design. Transport checks apply to remote servers; scrutiny shifts to §1/§2.
PASS	No known vulnerabilities (OSV.dev)	§4.1	No advisories on record for @trusty-squire/mcp @1.1.4 (npm).
PASS	Server-supplied instructions free of poisoning indicators	§5.1–§5.4	No poisoning indicators found across 19 server-supplied text item(s).

What this grade covers

Provenance & supply-chain integrity (§1)
Tool surface & capability risk (§2)
Transport & authentication (§3)
Known CVEs via OSV.dev (§4)
Instruction/tool poisoning patterns (§5)

Limitations: pattern-based only (no semantic injection detection), static npm analysis (live server instructions not retrieved for package-only scans), single-server scope (no cross-server toxic flow analysis). See the full policy.

Methodology: MCP Server Security Policy. Unfamiliar term? See the glossary.