Skills zapier-workflows

📦

zapier-workflows

Name: zapier-workflows
Author: davila7

Content revision r2 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Run and Document Zapier Workflows

Zapier workflows are difficult to recall and coordinate across sessions. This skill documents preferred tools and helps execute approved MCP actions or webhook automations.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "zapier-workflows" from https://skillstore.io/skills/davila7-zapier-workflows.md and its manifest at https://skillstore.io/api/skills/davila7-zapier-workflows/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/davila7-zapier-workflows.md Signed manifest GET /api/skills/davila7-zapier-workflows/manifest Signed lockfile GET /api/skills/davila7-zapier-workflows/lockfile

Test it

Using "zapier-workflows". Which workflow should handle my daily research digest?

Expected outcome:

The documented Daily AI Digest is the closest match. It gathers research and delivers a report, but it has not been triggered.

Using "zapier-workflows". Track a 42 dollar software expense in my preferred sheet.

Expected outcome:

Destination: Personal Budget sheet
Planned fields: amount 42 dollars, category software, date pending
Status: waiting for approval

Using "zapier-workflows". Create a repeatable competitor research process.

Expected outcome:

Recommended pattern: research each competitor, summarize comparable facts, review the results, then save approved findings to the selected sheet.

Security Audit

High Risk

v9 • 7/23/2026 Open versioned report

Sixty-three static alerts are false positives caused by Markdown formatting, expected Zapier endpoints, and standard Claude skill directories. One low-severity alert is confirmed because reset instructions redirect users to a different community repository. Semantic review found high-risk plaintext credential storage, unconfirmed automation execution, and persistent self-modification.

Files scanned

748

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (3)

High

SKILL.md:76-90 SKILL.md:147-150

Plaintext Storage of Webhook Credentials

The skill stores webhook URLs in reference files even though those URLs authorize Zap execution. File disclosure or accidental commits can expose automation access.

The source explicitly says webhook URLs contain authentication tokens and are stored in plaintext. This is a direct credential-handling design decision.

High

SKILL.md:211-220 SKILL.md:390-397

Side-Effecting Automations Run Without Confirmation

The execution sequence triggers webhook Zaps or MCP tools before confirmation. Broad trigger words can start costly or externally visible workflows without a final approval.

The ordered workflow places execution before confirmation and includes direct webhook POSTs. No preview, allowlist, or approval gate is specified.

High

SKILL.md:156-170 SKILL.md:260-271

Persistent Self-Modification From Conversational Input

The skill directs the agent to persist user-provided workflow text in instruction-adjacent files. Unvalidated content can influence later sessions and tool use.

The source explicitly requires self-editing and permanent pattern storage. It defines no schema validation or review boundary for persisted text.

Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Low

SKILL.md:499

Hardcoded URL

3. Re-clone from GitHub: https://github.com/AlexBoudreaux/claude-zapier-skill

The reset procedure redirects users from the audited marketplace source to a repository under another owner. Re-cloning unpinned community code adds supply-chain risk.

Risk Factors

⚙️ External commands (43)

🌐 Network access (9)

SKILL.md:21 SKILL.md:106 SKILL.md:123 SKILL.md:219 SKILL.md:293 SKILL.md:301 SKILL.md:427 SKILL.md:453 SKILL.md:499

📁 Filesystem access (11)

SKILL.md:64 SKILL.md:81 SKILL.md:465 SKILL.md:500 SKILL.md:523 SKILL.md:64 SKILL.md:69 SKILL.md:81 SKILL.md:465 SKILL.md:500 SKILL.md:523

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/davila7-zapier-workflows/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/davila7-zapier-workflows/security.svg)](https://skillstore.io/skills/davila7-zapier-workflows?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/davila7-zapier-workflows?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-zapier-workflows/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-zapier-workflows.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

davila7. (2026). zapier-workflows security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-zapier-workflows/audits/9

BibTeX citation

@techreport{davila7-davila7-zapier-workflows-2026,
  author = {davila7},
  title = {zapier-workflows security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-zapier-workflows/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "zapier-workflows security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-zapier-workflows/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-zapier-workflows:audit:9"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Run Recurring Operations

Match a named request to a documented multi-step Zap, present its effects, and trigger it after approval.

Research and Record Findings

Use documented research tools, summarize results, and save approved findings to a preferred Google Sheet.

Track Sales Activity

Coordinate approved lead enrichment and tracking actions through available Zapier MCP tools.

Try These Prompts

Review Available Automations

List my documented Zaps and explain which one best matches [goal]. Do not run anything.

Record an Expense

Use my documented Google Sheets preference to record [expense details]. Show the planned fields and request approval before writing.

Research and Save Results

Research [topic] with my documented tools, summarize the findings, then request approval before saving them to [destination].

Design an Advanced Workflow

Design a repeatable workflow for [goal] using my available Zapier tools. Compare MCP orchestration with existing Zaps and include approval and failure handling.

Best Practices

Review the target, inputs, costs, and external effects before approving any automation.
Keep webhook credentials outside skill files and rotate any URL that was exposed.
Use precise trigger phrases and verify connected tool permissions regularly.

Avoid

Do not trigger workflows from ambiguous requests or broad words such as run.
Do not store real webhook URLs in repositories or shared skill files.
Do not persist conversational instructions without validation and explicit approval.