updated 2026-10-06 08:17 UTC

Agent Vision Toolkit

Repository Website by Anionex

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Agent Skills Python Listed MIT

Is Agent Vision Toolkit safe? Thin or incomplete trust evidence. Review carefully before production use.

OSSF Scorecard 4.6 / 10
Provenance None
Signed commits 23%
Last push 4d ago
Compare Agent Vision Toolkit

How does it stack up against its Agent Skills neighbours?

Pick any agent to compare →
Suggest a correction

In detail: Agent Vision Toolkit scores 47.6/100 (Grade D), ranked #261 of 359 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 4.6/10; 23% of recent commits are signed; last pushed 2026-10-02. Every point is earned from checkable signals — never paid placement. How scoring works →

How Agent Vision Toolkit could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships Agent Vision Toolkit and whether that has changed: from the source repository, through how changes are reviewed and released, to the code you run. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities and, for skills, AST02 Supply Chain Compromise.

  1. Source Partly signed

    github.com/Anionex/agent-vision-toolkit, MIT, last pushed 2026-10-02. 23% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 4.6/10 (scanned Sep 25, 2026). The checks that decide who can get a change released:

    • Code Review1
    • Branch Protection0
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions10
    • Pinned Dependencies0
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 0
    CI-Tests 8
    CII-Best-Practices 0
    Code-Review 1
    Contributors 3
    Dangerous-Workflow 10
    Dependency-Update-Tool 0
    Fuzzing 0
    License 10
    Maintained 0
    Packaging -1
    Pinned-Dependencies 0
    SAST 0
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 10
    Vulnerabilities 9

  3. Published packages None

    No registry package. Agent Vision Toolkit is used from its repository, so what you run is whatever you check out: pin a release tag or commit.

Changes to this chain

  • 2026-09-01 OSSF Scorecard: 4.6/10

Evidence behind this score

Coverage C: 2 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads (missing)
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions (missing)

Verify this score yourself

Every build re-issues Agent Vision Toolkit’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read the skill’s instructions for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you install it, such as Cisco Skill Scanner.

How Agent Vision Toolkit compares in Agent Skills

  1. #259 Creative Writing Skills 48.3 +0.7
  2. #260 Opengap 47.7 +0.1
  3. #261 Agent Vision Toolkit 47.6 this agent
  4. #262 Working Activity 47.6 ±0
  5. #263 Dashi Ppt Skill 47.5 −0.1

Bars show each HVTrust score; the tick marks Agent Vision Toolkit’s 47.6.

Where the 47.6 comes from

HVTrust dimensions vs the Agent Skills average

47.6 / 100 · 100.0% confidence

Agent Vision Toolkit Agent Skills average (359 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
6.9 / 25
1.0 below avg 7.9
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
0.6 below avg 11.4
Transparency50% declared license · 50% OSSF Scorecard
12.4 / 17
in line with avg 12.2
Maintenance60% last-push freshness · 40% commit activity
11.7 / 20
2.4 below avg 14.1
AdoptionLog-scaled stars · package downloads
7.4 / 20
1.6 below avg 9.0

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-10-02
Rank Moved
Rank rose 27 spots (#287 → #260)
2026-09-26
Rank Moved
Rank dropped 10 spots (#270 → #280)
2026-09-25
Rank Moved
Rank dropped 24 spots (#246 → #270)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 4.6/10. Tighten the weakest checks to improve public safety evidence.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.
Compare with another agent Get email alerts for Agent Vision Toolkit View Agent Skills Report missing data
51.0
Activity sub-score · out of 100
#261
In Agent Skills

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade D reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-06 08:17 UTC · Repo last pushed 4 days ago

Rank Trend

2026-09-29 2026-10-06

Activity & Reach

Stars
1.2k
Forks
49
Last Push
2026-10-02
4 days ago
Commits (4 wk)
0
Downloads (7d)
—
HN mentions (30d)
—
Open Issues
4
Rank Change
▼2
was #259

Analysis

Activity Inputs

51.0 / 100
StarsRepository reach
18.5 / 30
FreshnessLast push recency
24.4 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
7.9 / 20

Common questions about Agent Vision Toolkit

Public trust evidence for Agent Vision Toolkit is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.
Does Agent Vision Toolkit publish package provenance?
No published build provenance is currently detected for Agent Vision Toolkit. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does Agent Vision Toolkit have an OpenSSF Scorecard?
Agent Vision Toolkit has an OpenSSF Scorecard score of 4.6/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is Agent Vision Toolkit actively maintained?
Actively maintained. The repository was pushed to within the last 4 day(s).
What license does Agent Vision Toolkit use?
Agent Vision Toolkit ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Agent Vision Toolkit's commits signed?
23% of the last 100 commits to Agent Vision Toolkit are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
None detected
No MCP server signal detected.
Detailed evidence is not shown in the public view.
External Service Dependencies
low confidence
None detected
No clear third-party provider dependency detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
high confidence
Extensions
Extension based plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
N/A
No package source configured
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live
How this surface has changed

Detected changes to Agent Vision Toolkit's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-09-23
Tool Surface Changed
Detected tool/plugin surface changed: none → extension-based

Maintain Agent Vision Toolkit?

For maintainers

HVTrust scores Agent Vision Toolkit from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Rank 14Listed 2HVTrust 2Grade 2Scorecard 1Delisted 1Surface 1
2026-10-02
Rank Moved
Rank rose 27 spots (#287 → #260)
2026-09-26
Rank Moved
Rank dropped 10 spots (#270 → #280)
2026-09-25
Rank Moved
Rank dropped 24 spots (#246 → #270)
2026-09-23
Tool Surface Changed
Detected tool/plugin surface changed: none → extension-based
2026-09-23
Rank Moved
Rank dropped 94 spots (#147 → #241)
2026-09-23
HVTrust Changed
HVTrust up 7.9pts (40.1 → 48.0)
2026-09-22
Newly Listed
First tracked at rank #147
2026-09-21
Removed From Active Tracking
Removed from active tracking
2026-09-20
Rank Moved
Rank dropped 19 spots (#221 → #240)
2026-09-19
Grade Changed
Trust grade C → D
2026-09-16
Rank Moved
Rank dropped 18 spots (#184 → #202)
2026-09-13
Rank Moved
Rank dropped 15 spots (#166 → #181)
2026-09-05
Rank Moved
Rank dropped 32 spots (#105 → #137)
2026-09-01
Scorecard Added
OSSF Scorecard: 4.6/10
2026-09-01
Grade Changed
Trust grade D → C
2026-09-01
Rank Moved
Rank rose 179 spots (#272 → #93)
2026-09-01
HVTrust Changed
HVTrust up 33.3pts (22.2 → 55.5)
2026-08-30
Rank Moved
Rank dropped 20 spots (#243 → #263)
2026-08-29
Rank Moved
Rank dropped 25 spots (#218 → #243)
2026-08-28
Rank Moved
Rank dropped 17 spots (#201 → #218)
2026-08-27
Rank Moved
Rank dropped 11 spots (#190 → #201)
2026-08-26
Rank Moved
Rank dropped 88 spots (#102 → #190)
2026-08-16
Newly Listed
First tracked at rank #102
GitHub → Website →

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 47.6 Grade D
Markdown:
[![HVTrust](https://hvtracker.net/badge/agent-vision-toolkit.svg)](https://hvtracker.net/agents/agent-vision-toolkit)
HTML:
<a href="https://hvtracker.net/agents/agent-vision-toolkit"><img src="https://hvtracker.net/badge/agent-vision-toolkit.svg" alt="HVTrust"></a>

Other agents in Agent Skills

Data sources
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON