MCP server · trust report

dev.redeal/redeal

3 checks that ran failed — injection surface, credential hygiene and transport config — so this release can’t be trusted as-is.

Publisher
dev.redeal
Repository
github.com/redeal-dev/redeal
Install
remote only
Versions
7
MCP revision
2025-11-25 · superseded
Inspected
5 of 6 checks · 85%
Scored
2026-09-01 · 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 checks1 clean4 flagged1 not inspected
  • Injection surface

    fail25% of grade

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

    tool "get_entropy" description: names an outbound copy/exfil destination (BCC/exfil verb).

  • Supply chain

    pass25% of grade

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

    repository linkage verified

  • Credential hygiene

    fail15% of grade

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

    tool "commit_input" has a secret-shaped input parameter "invite_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "create_deal" has a secret-shaped input parameter "api_key" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_certificate" has a secret-shaped input parameter "credential" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_deal" has a secret-shaped input parameter "credential" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_entropy" has a secret-shaped input parameter "credential" — secrets must never be tool parameters (the model would supply/handle the credential). tool "reveal_input" has a secret-shaped input parameter "invite_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "validate_input" has a secret-shaped input parameter "invite_token" — secrets must never be tool parameters (the model would supply/handle the credential).

  • Permission scope

    unscannable15% of grade

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

    No source files, package.json, or pyproject were fetched; cannot infer capability scope.

  • Version behavior

    warn10% of grade

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

    vs prior 0.6.0 (minor bump): tool "create_deal" gained input property(ies): visibility; new tool "get_public_certificate" touches a sensitive surface (email/exec/net/fs).

  • Transport config

    fail10% of grade

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

    remote MCP endpoint declares NO authentication (unauthenticated remote — nginx-ui/CVE-2026-33032 class)

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
v0.7.0 · current2026-08-19 D455/6 · 85%±0
v0.6.02026-08-18 D504/6 · 75%±0
v0.4.02026-08-17 D505/6 · 85%±0
v0.2.02026-08-16 D455/6 · 85%±0
v0.1.02026-08-15 D504/6 · 75%