Agent skill · Audited from source

Commit Helper

skill · agentforce314/clawcodexMIT licenceAudited 19 Oct 2026 · source 63a5da270dd1

★ 911pushed today
✓SAFEGrade B · 89/100 · 19 Oct 2026 · 63a5da2
911repo stars · whole agentforce314/clawcodex

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 63a5da270dd1 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Generate a conventional-commit message from staged changes.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Commit Helper (agentforce314/clawcodex)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/agentforce314/commit-helper

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS1
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

LOWInventory / provenanceskill.no_frontmatter · SKILL.md:1
F-13 Inventory / provenanceCWE-1104Layer L3
Why
SKILL.md lacks name/description frontmatter
Fix
—

Audit 0.4.1 · source sha 63a5da270dd1 · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheragentforce314 GitHub userOwner of the repository this skill is read from
  • Source folderagentforce314/clawcodex/tests/fixtures/skills/commit-helperThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict63a5da270dd1A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Generate a conventional-commit message from staged changes.

---
description: Generate a conventional-commit message from staged changes.
allowed-tools: [Bash, Read]
arguments: [scope]
argument-hint: <scope>
---
# Commit Helper

Run `git diff --cached` and produce a conventional-commit message in `$scope` scope.
Skill base: ${CLAUDE_SKILL_DIR}
Session: ${CLAUDE_SESSION_ID}

Excerpt, first 314 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 63a5da2

Download folder ↗
git clone https://github.com/agentforce314/clawcodex
git -C clawcodex checkout 63a5da270dd1

The author documents no install command, so this uses the repository directly. Our verdict covers commit 63a5da270dd1 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 63a5da270dd1

Questions about Commit Helper

What does the Commit Helper skill do?
Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.
Is Commit Helper safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Commit Helper access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (63a5da270dd1), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.