Skills/npm/softr-vibe-coding

softr-vibe-coding@2.26.0

VERIFIED· install only

Publisher claims: "Claude Code skill for building and fixing Softr apps: Vibe Coding blocks (TSX/JSX), Softr MCP work, Custom Code CSS for Softr's header and navigation, and app QA. Installs into ~/.claude/skills/ and auto-updates on each Claude Code session." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher leo-softr · publishing for 184 daysInstalls 2,494Last detonated 14 min ago
$claude mcp add softr-vibe-coding -- npx -y softr-vibe-coding
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
2 of 2 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 2.25.0

vet-skills diff softr-vibe-coding 2.25.0 2.26.0

In the sandbox, this version reached for nothing 2.25.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: [x] Cancelled.
0.2sprocess2 of 2 bundled scripts run with no arguments
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentreferences/modal-pages.md:128 · HTML comment carrying imperative instructions to the agentLIVE-CHECK: after one click on the button, run f=document.querySelector('[data-softr-dialog-type="OPEN_PAGE"] iframe'); [f.contentWindow.location.href, !!f.contFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/modal-pages.md:119 · HTML comment carrying imperative instructions to the agentLIVE-CHECK: on any staff page in the preview, run performance.getEntriesByType('resource').map(r=>r.name).filter(n=>n.includes('/blocks/navigation/')) and [...dFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/modal-pages.md:161 · HTML comment carrying imperative instructions to the agentLIVE-CHECK: in the parent run addEventListener('app:probe',e=>window.__got=e.detail); from the iframe run window.parent.dispatchEvent(new CustomEvent('app:probeFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentSKILL.md:375 · HTML comment carrying imperative instructions to the agentLIVE-CHECK: drop "not yet run live" once the modal-pages.md live check has runFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:55 · npx invocation of non-well-known package — may execute untrusted code…arkdown to `./DESIGN.md` in the project root**), or the CLI fallback when not (`npx -y dembrandt@latest <url> --design-md --crawl 5`, then copy `output/<domain>/DESIG…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationpackage.json:4 · Auto-update or dynamic fetch configuration — agent may load new code at runtime… Softr's header and navigation, and app QA. Installs into ~/.claude/skills/ and auto-updates on each Claude Code session.", "bin": { "softr-vibe-coding": "cli/cli.js" }, "files": [ "cli/…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collapsed <details> block carrying instructionsREADME.md:56 · Collapsed <details> block carrying instructions<summary>Download the latest tarball</summary> ```bash mkdir -p ~/.claude/skills/softr-vibe-coding curl -L https://github.com/leo-softr/Softr-Vibe-Coding-Block-Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagecli/cli.js:15 · npx invocation of non-well-known package — may execute untrusted codevar HOOK_COMMAND = 'npx -y --prefer-online ' + SKILL_NAME + '@latest sync';Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagecli/cli.js:120 · npx invocation of non-well-known package — may execute untrusted codeconsole.log('Usage: npx ' + SKILL_NAME + '@latest <command>');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/modal-pages.md:13 · HTML comment carrying imperative instructions to the agentLIVE-CHECK: after the live check in Softr <> HubSpot Demo, replace the sentence "Nothing here had been run in a live app when it was written" with the result, aFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Rule modification attemptreferences/date-picker.md:284 · Rule modification attempt — overwriting existing instructions · informational: not an instruction filecalendar off at the card's edge. Same rule as Combo rule 1: no clipping class on anything thatFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Auto-update or dynamic fetch configurationcli/cli.js:124 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconsole.log(' and adds a SessionStart hook to auto-update on each Claude Code session.');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈25,223 tok
1 file · 46 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.