Waxell

plugin

protect-mcp High risk

wshobsonwshobson/agentsupdated

Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin, receipts independently verifiable offline.
wshobson's own description, from the plugin's files.
Stars
42,753
Version
v3
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 30 findings, highest severity high.

Highest severity
high
Findings
30
What ran
Static analysis + deep scan

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the plugin's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked 2 days ago

Result

High risk Waxell rates it high risk: 30 findings, highest severity high.

Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work

Findings (30)

high · 12

  • high

    Tool Misuse: Chaining Abuse

    README.md:135 · skillspector:TM2

  • high

    Tool Misuse: Chaining Abuse

    agents/policy-enforcer.md:59 · skillspector:TM2

  • high

    Tool Misuse: Tool Parameter Abuse

    test/README.md:15 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    test/fixtures/pretool-deny-bash-destructive.json:4 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    test/README.md:41 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    test/README.md:41 · skillspector:TM1

  • high

    Privilege Escalation: Credential Access

    test/fixtures/pretool-deny-write.json:4 · skillspector:PE3

  • high

    Tool Misuse: Tool Parameter Abuse

    test/README.md:15 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    test/README.md:41 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    test/fixtures/pretool-deny-bash-destructive.json:4 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    test/run-tests.sh:85 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    test/run-tests.sh:85 · skillspector:TM1

medium · 18

  • medium

    Agent Snooping: Skill Enumeration

    README.md:29 · skillspector:AS3

  • medium

    Agent Snooping: Skill Enumeration

    README.md:48 · skillspector:AS3

  • medium

    Privilege Escalation: Sudo/Root Execution

    README.md:37 · skillspector:PE2

  • medium

    Privilege Escalation: Sudo/Root Execution

    skills/protect-mcp-setup/SKILL.md:53 · skillspector:PE2

  • medium

    Privilege Escalation: Sudo/Root Execution

    test/run-tests.sh:104 · skillspector:PE2

  • medium

    Privilege Escalation: Sudo/Root Execution

    README.md:200 · skillspector:PE2

  • medium

    Excessive Agency: Unrestricted Tool Access

    agents/policy-enforcer.md:70 · skillspector:EA1

  • medium

    Excessive Agency: Unrestricted Tool Access

    agents/policy-enforcer.md:144 · skillspector:EA1

  • medium

    Excessive Agency: Autonomous Decision Making

    agents/policy-enforcer.md:242 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    agents/policy-enforcer.md:269 · skillspector:EA2

  • medium

    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub

    hooks/evaluate.sh:38 · skillspector:RP1

  • medium

    Bundled lifecycle hooks can run automatically when their configured events occur, so their reach and handler capability

    hooks/hooks.json:1 · skillspector:BH1

  • medium

    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub

    skills/protect-mcp-setup/SKILL.md:22 · skillspector:RP1

  • medium

    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub

    test/run-tests.sh:26 · skillspector:RP1

  • medium

    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub

    test/run-tests.sh:242 · skillspector:RP1

  • medium

    Tells Claude to install packages (@veritasacta/verify@0.11.1)

    README.md:20 · skill_risk:S3

  • medium

    Tells Claude to install packages (@veritasacta/verify@0.11.1)

    commands/audit-chain.md:82 · skill_risk:S3

  • medium

    Tells Claude to install packages (@veritasacta/verify@0.11.1)

    commands/verify-receipt.md:12 · skill_risk:S3

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

  1. v3 (0.2.0)2026-11-192 added, 13 changed High riskgot riskier
  2. v2 (0.1.6)2026-11-166 changed No issues
  3. v1 (0.1.5)2026-11-03 No issues

Files

Files

24 files, 94 KB in total. Names only; open them on GitHub.

  • .claude-plugin/plugin.json
  • .codex-plugin/plugin.json
  • README.md
  • agents/policy-enforcer.md
  • agents/receipt-verifier.md
  • commands/audit-chain.md
  • commands/verify-receipt.md
  • hooks/evaluate.sh
  • hooks/hooks.json
  • hooks/sign.sh
  • skills/protect-mcp-setup/SKILL.md
  • skills/protect-mcp-setup/references/receipt-format.md
  • test/README.md
  • test/expected/receipt-schema.json
  • test/fixtures/posttool-signing-input.json
  • test/fixtures/pretool-allow-bash-safe.json
  • test/fixtures/pretool-allow-read.json
  • test/fixtures/pretool-deny-bash-destructive.json
  • test/fixtures/pretool-deny-write.json
  • test/fixtures/test-policy.cedar
  • test/hook-migration.mjs
  • test/hook-readback.mjs
  • test/run-tests.sh
  • test/verify-fixtures.sh

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More engineering skills and plugins

See all