Waxell

skill

matting High risk

zrongzrong/skillsupdated

通过独立 matting-api 为本地图片抠图、去背景并输出透明 PNG。每次先读取服务状态、队列、实时算法和模型能力,再检查输入图的 alpha、边框颜色、均匀度与亮度特征,自动选择可用的 BiRefNet、InSPyReNet、Luma 或 CorridorKey 组合;也支持显式算法/模型。用户提到抠图、去背景、透明底、绿幕/蓝幕、人物/产品/Logo/特效分离时使用。配置缺失或服务不可用时,由调用方明确回退到现有本地方法,不能伪装成 matting-api 成功。
zrong's own description, from the skill's files.
Stars
15
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 7 findings, highest severity high.

Highest severity
high
Findings
7
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 today

Result

High risk Waxell rates it high risk: 7 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 (7)

high · 4

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:38 · skillspector:AE1

  • high

    The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing

    scripts/matting_cli/client.py:1 · skillspector:LP1

  • high

    The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing per

    scripts/matting_cli/config.py:1 · skillspector:LP1

  • high

    The skill uses 'file_write' capability that is not listed in its permissions. This may indicate deceptive intent or miss

    scripts/tests/test_agent_config.py:1 · skillspector:LP1

low · 3

  • low

    Supply Chain: Unverifiable Dependency: httpx has 2 known advisory(ies) (CVE-2021-41945 (Improper Input Validation in htt

    scripts/pyproject.toml:7 · skillspector:SC4

  • low

    Supply Chain: Unverifiable Dependency: pillow has 16 known advisory(ies) (CVE-2026-112390 (Pillow: Infinite loop in MIC

    scripts/pyproject.toml:8 · skillspector:SC4

  • low

    Supply Chain: Unverifiable Dependency: pytest has 2 known advisory(ies) (CVE-2025-71176 (pytest has vulnerable tmpdir ha

    scripts/pyproject.toml:20 · skillspector:SC4

Versions

Version history

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

  1. v22026-11-212 changed High riskgot riskier
  2. v1 (26.36.56)2026-11-03 No issues

Files

Files

20 files, 60 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • agent_config.example.toml
  • evals/evals.json
  • references/algorithm-selection.md
  • references/api-contract.md
  • references/configuration.md
  • scripts/matting_cli/__init__.py
  • scripts/matting_cli/agent_config.py
  • scripts/matting_cli/cli.py
  • scripts/matting_cli/client.py
  • scripts/matting_cli/config.py
  • scripts/matting_cli/errors.py
  • scripts/matting_cli/inspection.py
  • scripts/matting_cli/selection.py
  • scripts/matting_cli/service.py
  • scripts/pyproject.toml
  • scripts/tests/conftest.py
  • scripts/tests/test_agent_config.py
  • scripts/tests/test_inspection_selection.py
  • scripts/tests/test_service.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 design skills and plugins

See all