MCP server · trust report

io.github.creator35lwb-web/verifimind-genesis

1 check that ran failed — version behavior — so this release can’t be trusted as-is.

Publisher
io.github.creator35lwb-web
Repository
github.com/creator35lwb-web/VerifiMind-PEAS
Install
remote only
Versions
41
MCP revision
2025-11-25 · superseded
Inspected
5 of 6 checks · 75%
Scored
2026-09-04 · rubric 1.0.0

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

6 checks3 clean2 flagged1 not inspected
  • Injection surface

    unscannable25% of grade

    Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

    No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

  • Supply chain

    pass25% of grade

    Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

    repository linkage verified

  • Credential hygiene

    pass15% of grade

    How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

    No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

  • Permission scope

    pass15% of grade

    Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

    No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

  • Version behavior

    fail10% of grade

    Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

    vs prior 3.38.0 (minor bump): new hardcoded outbound host/BCC destination(s): aistudio.google.com, api.pinata.cloud, console.anthropic.com, console.groq.com, console.mistral.ai, ipfs.io, ollama.ai, platform.openai.com, polygon-rpc.com.

  • Transport config

    warn10% of grade

    Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

    remote endpoint present with no declared auth mode (unable to confirm authentication); manifest/source references Tracking behavior — disclosure

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v3.39.0 · current2026-08-22 B855/6 · 75%C→B in v3.39.0
v3.38.02026-08-18 C705/6 · 85%B→C in v3.38.0
v3.36.02026-08-13 B955/6 · 75%±0
v3.35.02026-08-07 B955/6 · 75%C→B in v3.35.0
v3.34.02026-08-06 C706/6 · 100%B→C in v3.34.0
v3.31.02026-07-23 B954/6 · 65%±0
v3.30.02026-07-22 B954/6 · 65%±0
v3.27.02026-07-20 B955/6 · 75%±0
v3.26.02026-07-16 B954/6 · 65%±0
v3.5.02026-05-13 B954/6 · 65%