Waxell

skill

huawei-cloud-vod-collector High risk

huaweicloudhuaweicloud/huaweicloud-skillsupdated

Invoke this skill to capture poor experiences and distill them into high-value requirements (Voice of Developer). Use when user encounters any Huawei Cloud related issues, like user expresses dissatisfaction, encounters errors, or wants to report issues/suggestions.Triggers include: "体验差","反馈问题","反馈建议","这个有bug","拒绝了请求","报告问题","反馈体验","report a problem","report a suggestion","bug report","poor experience","voice of developer"
huaweicloud's own description, from the skill's files.
Stars
59
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 40 findings, highest severity critical.

Highest severity
critical
Findings
40
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 skill's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked yesterday

Result

High risk Waxell rates it high risk: 40 findings, highest severity critical.

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 (40)

critical · 3

  • critical

    Data Flow: Tainted flow: 'request' from os.environ.get (line 135, credential/environment) → urllib.request.urlopen (netw

    scripts/install_cli.py:136 · skillspector:TT3

  • critical

    Data Flow: Tainted flow: 'request' from os.environ.get (line 163, credential/environment) → urllib.request.urlopen (netw

    scripts/install_cli.py:164 · skillspector:TT3

  • critical

    Data Flow: Tainted flow: 'req' from os.environ.get (line 538, credential/environment) → urllib.request.urlopen (network

    scripts/vod_deliver.py:546 · skillspector:TT3

high · 12

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:87 · skillspector:AE1

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:109 · skillspector:AE1

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:116 · skillspector:AE1

  • high

    Supply Chain: External Script Fetching

    scripts/install_cli.sh:31 · skillspector:SC2

  • high

    Tool Misuse: Tool Parameter Abuse

    scripts/vod_deliver.py:116 · skillspector:TM1

  • high

    Data Exfiltration: Env Variable Harvesting

    tests/test_install_cli.py:140 · skillspector:E2

  • high

    Data Exfiltration: Env Variable Harvesting

    tests/test_install_cli.py:351 · skillspector:E2

  • high

    Data Exfiltration: Env Variable Harvesting

    tests/test_install_cli.py:436 · skillspector:E2

  • high

    Data Exfiltration: Env Variable Harvesting

    tests/test_md_io_roundtrip.py:63 · skillspector:E2

  • high

    Data Flow: Direct flow: os.environ.get (credential/environment) → subprocess.run (code execution)

    tests/test_install_cli.py:347 · skillspector:TT1

  • high

    Tells Claude to install unpinned packages (pyyaml)

    scripts/vod_deliver.py:22 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (tomli)

    scripts/vod_deliver.py:272 · skill_risk:S2

medium · 21

  • medium

    Without declared permissions the skill's intent is opaque and cannot be validated.

    SKILL.md:1 · skillspector:LP3

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:166 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:195 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:210 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:236 · skillspector:EA2

  • medium

    Rogue Agent: Session Persistence

    references/cli-installation-guide.md:100 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    references/cli-installation-guide.md:100 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    references/iam-policies.md:27 · skillspector:RA2

  • medium

    Data Flow: Tainted flow: 'dest' from os.environ.get (line 162, credential/environment) → open (file write)

    scripts/install_cli.py:165 · skillspector:TT2

  • medium

    Data Flow: Tainted flow: 'lock_path' from pathlib.Path.read_text (line 50, file read) → open (file write)

    scripts/md_io.py:55 · skillspector:TT2

  • medium

    Data Flow: Tainted flow: 'file_path' from pathlib.Path.read_text (line 843, file read) → open (file write)

    scripts/md_io.py:241 · skillspector:TT2

  • medium

    Dangerous Code Execution: subprocess module call

    scripts/vod_deliver.py:1236 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    scripts/vod_deliver.py:1261 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_install_cli.py:142 · skillspector:AST4

  • medium

    Data Flow: Tainted flow: 'args' from os.environ.get (line 344, credential/environment) → subprocess.run (code execution)

    tests/test_install_cli.py:142 · skillspector:TT2

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_install_cli.py:347 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_install_cli.py:450 · skillspector:AST4

  • medium

    Data Flow: Tainted flow: 'command' from os.environ.get (line 445, credential/environment) → subprocess.run (code executi

    tests/test_install_cli.py:450 · skillspector:TT2

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_install_cli.py:460 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_md_io_roundtrip.py:65 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_vod_deliver_dedup_notify.py:360 · skillspector:AST4

low · 4

  • low

    Supply Chain: Unpinned Dependencies

    requirements.txt:1 · skillspector:SC1

  • low

    Supply Chain: Unverifiable Dependency: pyyaml has 8 known advisory(ies) (CVE-2019-20477 (Deserialization of Untrusted Da

    requirements.txt:1 · skillspector:SC4

  • low

    Supply Chain: Unpinned Dependencies

    requirements.txt:2 · skillspector:SC1

  • low

    Dangerous Code Execution: Dynamic attribute access via getattr()

    tests/test_vod_deliver_windows.py:35 · skillspector:AST7

Versions

Version history

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

  1. v22026-11-167 added, 11 changed High riskgot riskier
  2. v12026-11-03 Review findings

Files

Files

29 files, 258 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • assets/VOD_FEEDBACKS.md
  • assets/VOD_ISSUE.md
  • assets/config.yaml
  • hooks/hermes/hooks.yaml
  • hooks/openclaw/hooks.yaml
  • references/acceptance-criteria.md
  • references/cli-installation-guide.md
  • references/dedup-and-notify.md
  • references/hooks-setup.md
  • references/iam-policies.md
  • references/openclaw-integration.md
  • references/verification-method.md
  • requirements.txt
  • scripts/ensure_cli.ps1
  • scripts/ensure_cli.sh
  • scripts/hcloud-run.sh
  • scripts/install_cli.py
  • scripts/install_cli.sh
  • scripts/md_io.py
  • scripts/models.py
  • scripts/vod_deliver.py
  • scripts/vod_install.ps1
  • scripts/vod_install.sh
  • scripts/vod_sanitize.py
  • tests/test_install_cli.py
  • tests/test_md_io_roundtrip.py
  • tests/test_vod_deliver_dedup_notify.py
  • tests/test_vod_deliver_windows.py

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 documents skills and plugins

See all