Versioned security assessment

Report ID: SA-60320253

7/1/2026, 2:56:19 AM

obsidian-helper security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
obsidian-helper
Version
v2
Maintainer
Claude Code
Source
github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/obsidian-helper
Coverage
8 Files scanned · 1,150 Lines analyzed
Policy version
Unavailable

Confirmed finding summary

No confirmed security findings

The completed audit recorded no confirmed security findings. This is not proof that the Skill has no side effects.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Static analysis reported many high-risk patterns, but most are Markdown examples, Dataview syntax, or local setup instructions rather than executable skill code. Confirmed risks are medium severity: the skill guides broad Obsidian vault reads and writes, asks users to edit Claude Code MCP config, and handles a local API key. No evidence found for malicious exfiltration, remote command-and-control, hidden payloads, or prompt injection aimed at bypassing marketplace review.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

8 Files scanned · 1,150 Lines analyzed

3 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 3 evidence locations

Filesystem access

May read or write local files.

Observed in 5 evidence locations

Env variables

May read values from the process environment.

Observed in 3 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 3 evidence locations

Capability review items (3)
Medium
SKILL.md:493-504references/mcp-tools-reference.md:39-90
Broad Obsidian Vault Read and Write Access
TRUE_POSITIVE. The skill depends on MCP tools that list, read, search, append, and patch Obsidian vault content. This is legitimate for the advertised workflow, but it exposes private notes and can modify user data if misused.
The documented required tools explicitly include vault listing, file reads, batch reads, searches, appends, and patches. The risk is semantic and intentional rather than hidden malicious behavior.
Medium
SKILL.md:64-82README.md:17-25
Shell Setup Writes Claude Code MCP Configuration
TRUE_POSITIVE. The setup guidance includes terminal commands that create a Claude configuration directory and append MCP server configuration. This is a real local configuration change, though it is presented as user-run setup documentation.
The commands are visible setup instructions and include writes under the Claude configuration path. They do not show dynamic command injection or covert execution by the skill.
Medium
SKILL.md:60-77SKILL.md:85-95
Local API Key Stored in MCP Environment Configuration
TRUE_POSITIVE. The skill instructs users to place an Obsidian Local REST API key in MCP environment configuration. This is expected for the integration, but it creates secret-handling risk if the config is shared or exposed.
The referenced lines explicitly mention copying an API key and setting OBSIDIAN_API_KEY. The endpoint is local, so there is no evidence of exfiltration.

Risk findings

Confirmed security concerns are separated from items that still need review.

No confirmed security findings were recorded for this completed audit.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
Unavailable
Content hash
Unavailable
Tree hash
Unavailable
Skill path
Unavailable
Audit payload hash
Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Static false positives ignored (3)
Low
README.md:9-11references/dataview-queries.md:5-10references/mcp-tools-reference.md:9-19SKILL.md:30-35
Markdown Backticks Misclassified as Code Execution
FALSE_POSITIVE. Many external command findings are Markdown command names, slash commands, Dataview examples, or fenced examples. They are not executable Ruby backticks in source code.
The cited locations are Markdown tables or fenced documentation blocks. No runtime language file or executable backtick evaluation is present there.
Low
references/dataview-queries.md:5-10references/dataview-queries.md:26-31references/dataview-queries.md:35-41references/dataview-queries.md:45-50references/dataview-queries.md:54-58references/dataview-queries.md:62-67
Dataview Time Fields Misclassified as Weak Cryptography
FALSE_POSITIVE. The weak cryptography findings in Dataview references correspond to file metadata fields and query examples. No hashing or cryptographic algorithm usage is present.
The context is Dataview query syntax for sorting and filtering Obsidian notes. I did not find evidence of MD5, SHA1, DES, or similar weak crypto use.
Low
SKILL.md:77SKILL.md:95README.md:111-112
Hardcoded Network References Are Local or Dependency Links
FALSE_POSITIVE. The network findings are a local Obsidian REST endpoint and public dependency documentation links. No remote data upload or credential transmission target is shown.
The IP address is loopback and the README URLs identify Obsidian plugin and npm package dependencies. No suspicious external endpoint is present in the reviewed files.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable