Skills cocoindex

📦

cocoindex

Name: cocoindex
Author: davila7

Content revision r2 High Risk ⚡ Contains scripts🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands

Build CocoIndex Data Pipelines

Building incremental AI data pipelines requires coordinated sources, transformations, targets, and operations. This skill provides CocoIndex patterns for flows, custom functions, queries, and live updates.

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 "cocoindex" from https://skillstore.io/skills/davila7-cocoindex.md and its manifest at https://skillstore.io/api/skills/davila7-cocoindex/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-cocoindex.md Signed manifest GET /api/skills/davila7-cocoindex/manifest Signed lockfile GET /api/skills/davila7-cocoindex/lockfile

Test it

Using "cocoindex". Index product manuals from a local directory for semantic search in Qdrant.

Expected outcome:

Plan: Local document source, recursive text splitting, embedding generation, and Qdrant export.
Operations: Configure credentials locally, evaluate sample output, set up the named flow, then run an incremental update.

Using "cocoindex". Extract people and relationships from reports into Neo4j.

Expected outcome:

Schema: Typed person and relationship records with stable identifiers.
Flow: LLM extraction, normalized collectors, separate node and relationship exports, and validation before update.

Using "cocoindex". Keep a code search index synchronized while limiting memory use.

Expected outcome:

The proposed flow uses file change capture, language detection, chunked embeddings, bounded in-flight rows and bytes, and monitored live updates.

Security Audit

High Risk

v9 • 7/23/2026 Open versioned report

Most detections are documentation artifacts: CocoIndex .eval methods are not code evaluation, and Markdown backticks are not shell execution. However, the skill explicitly solicits API key values and includes examples that can expose credentials through configurable endpoints, terminal output, or process arguments. Forced reset and drop guidance also needs mandatory safeguards.

Files scanned

2,752

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (3)

High

references/cli_operations.md:319

Environment file access

cat .env | grep COCOINDEX_DATABASE_URL

The command reads a sensitive .env file and prints the database connection variable. This can disclose embedded credentials in terminal output, captured logs, or support transcripts.

High

SKILL.md:105-107

Unsafe Credential Solicitation

The skill says to "ask user to provide the API key value" and insists on obtaining a real key. This encourages secret disclosure in chat instead of local secret configuration.

The instruction explicitly requests API key values when environment variables are absent. The adjacent text rejects secret-free examples, so the credential-collection intent is unambiguous.

Medium

SKILL.md:271 SKILL.md:457-458 SKILL.md:469-472 SKILL.md:540-546

Destructive Flow Operations Lack Mandatory Safeguards

The main guide recommends forced setup, reset, drop, and drop-all operations without requiring confirmation, backups, or environment checks. These operations can remove persistent indexes and target data.

The cited commands explicitly bypass prompts, reset resources, or remove one or all flows. The main workflow does not require a user confirmation or production-scope check before presenting them.

Capability review items (7)

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

High

references/cli_operations.md:319

Database connection strings

cat .env | grep COCOINDEX_DATABASE_URL

The troubleshooting command reads .env and prints the complete COCOINDEX_DATABASE_URL. That URI can contain database usernames and passwords that then remain visible in terminal output or logs.

High

references/cli_operations.md:322

Database connection strings

psql $COCOINDEX_DATABASE_URL

Expanding the complete database URI into a psql command can expose embedded credentials through process listings and diagnostics. The guidance provides no safer credential-loading method.

High

references/custom_functions.md:401

Generic API/secret keys

api_key: str

The external API example stores an API key directly as a plain string field in a function specification. This can expose the secret through source configuration, serialization, logging, or object inspection.

High

references/custom_functions.md:410

Generic API/secret keys

headers={"Authorization": f"Bearer {self.spec.api_key}"}

The code sends a bearer API key to a configurable endpoint without an allowlist or HTTPS requirement. A malicious or mistaken endpoint can receive the credential.

High

SKILL.md:113

Database connection strings

COCOINDEX_DATABASE_URL=postgres://cocoindex:cocoindex@localhost/cocoindex

The guide recommends a fixed database username and password when configuration is absent. Although the host is localhost, reusing this default outside an isolated development system creates an insecure credential baseline.

High

SKILL.md:796

Database connection strings

- Test connection: `psql $COCOINDEX_DATABASE_URL`

Expanding the complete database URI into a psql command can expose embedded credentials through process listings and diagnostics. The guidance provides no safer credential-loading method.

Low

references/custom_functions.md:408

Python HTTP libraries

response = requests.get(

The example performs an outbound request to a configurable endpoint. It sends an Authorization header and lacks endpoint validation and a timeout, creating credential-disclosure and availability risks.

Risk Factors

⚡ Contains scripts (5)

references/api_operations.md:259 references/api_operations.md:290 references/api_operations.md:348 references/flow_patterns.md:328 SKILL.md:562

🌐 Network access (16)

references/api_operations.md:336 references/custom_functions.md:408 SKILL.md:26 SKILL.md:27 SKILL.md:89 SKILL.md:123 SKILL.md:234 SKILL.md:276 SKILL.md:356 SKILL.md:437 SKILL.md:489 SKILL.md:567 SKILL.md:675 SKILL.md:676 SKILL.md:830 SKILL.md:831

🔑 Env variables (44)

📁 Filesystem access (2)

references/cli_operations.md:39 references/cli_operations.md:325

⚙️ External commands (50)

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-cocoindex/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-cocoindex.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). cocoindex security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-cocoindex/audits/9

BibTeX citation

@techreport{davila7-davila7-cocoindex-2026,
  author = {davila7},
  title = {cocoindex security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-cocoindex/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: "cocoindex security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-cocoindex/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-cocoindex:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

Joseph OBrien Recommended

89jobrien-cocoindex

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 15

Updated

2026-08-21

davila7 Current

davila7-cocoindex

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Index Internal Documents

Create an incremental document pipeline with chunking, embeddings, metadata, and a vector database target.

Build Knowledge Graphs

Extract typed entities and relationships from documents, then export nodes and edges to a graph database.

Operate Live Indexes

Evaluate, deploy, monitor, and troubleshoot flows that continuously synchronize changing sources with search targets.

Try These Prompts

Create a Basic Flow

Create a CocoIndex flow that reads [file types] from [directory], splits text, and exports records to [target]. Explain dependencies and required configuration.

Build Vector Search

Design a CocoIndex pipeline for [content] using [embedding provider] and [vector database]. Include metadata, chunk settings, primary keys, and an evaluation plan.

Add a Custom Function

Create a typed CocoIndex custom function for [transformation]. Choose standalone or spec-executor form, explain caching, and define error handling without exposing secrets.

Design a Live Multi-Target System

Architect a live CocoIndex flow from [sources] to [targets]. Include change capture, concurrency limits, reusable query transforms, observability, rollback, and production safeguards.

Best Practices

Test transformations with evaluation before updating persistent targets.
Store credentials locally in environment variables or a secret manager, and never place secret values in prompts.
Confirm target scope and create backups before reset, drop, or schema-changing operations.

Avoid

Do not request API key values in conversation or print environment file contents.
Do not run reset or drop commands without explicit confirmation and environment verification.
Do not send source data or bearer tokens to unvalidated external endpoints.