Waxell

skill

segment-anything-model Review findings

orchestra-researchorchestra-research/ai-research-skillsupdated

Browse GitHub Download zipBook a demo
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
orchestra-research's own description, from the skill's files.
ResearchAI & agentsImages, video & audioskill
Stars
14,234
Version
v1
Copies
0
OverviewSecurity11Versions1

Overview

holdReview findings

Waxell's checks found 11 findings to review, highest severity high.

Highest severity
high
Findings
11
What ran
Static analysis

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 2 days ago

Result

Review findings Waxell's checks found 11 findings to review, highest severity high.

Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work

Findings (11)

high · 10

  • high

    Tells Claude to install unpinned packages (git+https://github.com/facebookresearch/segment-anything.git)

    SKILL.md:45 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (opencv-python, pycocotools, matplotlib)

    SKILL.md:48 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (transformers)

    SKILL.md:51 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (git+https://github.com/facebookresearch/segment-anything-2.git)

    references/advanced-usage.md:10 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (groundingdino-py)

    references/advanced-usage.md:52 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (git+https://github.com/facebookresearch/segment-anything.git)

    references/advanced-usage.md:53 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (torch, torchvision)

    references/troubleshooting.md:17 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (git+https://github.com/facebookresearch/segment-anything.git)

    references/troubleshooting.md:31 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (opencv-python, pycocotools, matplotlib, onnxruntime, onnx)

    references/troubleshooting.md:49 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (pycocotools-windows)

    references/troubleshooting.md:52 · skill_risk:S2

medium · 1

  • medium

    Tells Claude to install packages (onnx==1.14.0, onnxruntime==1.15.0)

    references/troubleshooting.md:340 · skill_risk:S3

Versions

Version history

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

One version so far: v1 (1.0.0), seen 2026-11-03.

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.

Book a demo

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 research skills and plugins

See all