MCP server · trust report

io.github.eltociear/skill-audit-mcp

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

Publisher
io.github.eltociear
Repository
github.com/eltociear/skill-audit-mcp
Install
oci:ghcr.io/eltociear/skill-audit-mcp:mcp-1.0.2
Versions
2
MCP revision
2025-06-18 · superseded
Inspected
6 of 6 checks · 100%
Scored
2026-09-03 · 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 clean3 flagged
  • 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 "audit_skill_text" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "audit_skill_url" 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

    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 1.0.2 (minor bump): new tool "paid_catalogue" touches a sensitive surface (email/exec/net/fs); new tool "air_quality" appeared; new tool "geocode" appeared; new tool "earthquakes" appeared; new tool "public_holidays" appeared; new tool "country_indicator" appeared; new tool "elevation" appeared; new tool "web_search" touches a sensitive surface (email/exec/net/fs); new tool "read_url" touches a sensitive surface (email/exec/net/fs); new tool "audit_skill_text" touches a sensitive surface (email/exec/net/fs); new tool "audit_skill_url" touches a sensitive surface (email/exec/net/fs); new hardcoded outbound host/BCC destination(s): github.com.

  • 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
v1.1.0 · current2026-07-29 D556/6 · 100%B→D in v1.1.0
v1.0.22026-06-07 B1003/6 · 55%