Versioned security assessment

Report ID: SA-B959EBFD

7/8/2026, 2:30:26 PM

web-search security assessment v3

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
web-search
Version
v3
Maintainer
101-skills
Source
github.com/101-skills/skills/tree/main/tools/llm/web-search/
Coverage
1 Files scanned · 153 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

2 confirmed security findings require attention.

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.

Most static findings are Markdown backticks, code fences, app identifiers, or documentation links. Real residual risk comes from visible external belt commands, the broad Bash(belt *) permission, and third-party handling of queries or extracted content. No prompt injection language or covert credential access was found.

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

1 Files scanned · 153 Lines analyzed

14 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 9 evidence locations

Filesystem access

May read or write local files.

Not recorded by this audit

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 25 evidence locations

Capability review items (12)
Medium
SKILL.md:7
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
The line instructs users to run npx skills add for another CLI skill, which can install external marketplace code. It is visible documentation, so confidence is moderate.
Medium
SKILL.md:19-24
Ruby/shell backtick execution
```bash
The quick start block includes belt login and belt app run commands. These are intentional commands, but they execute an external CLI against hosted services.
Medium
SKILL.md:48-52
Ruby/shell backtick execution
```bash
This range contains a visible belt CLI command that sends user input to hosted services. The workflow is intentional, but it still represents external command execution.
Medium
SKILL.md:58-62
Ruby/shell backtick execution
```bash
This range contains a visible belt CLI command that sends user input to hosted services. The workflow is intentional, but it still represents external command execution.
Medium
SKILL.md:68-72
Ruby/shell backtick execution
```bash
This range contains a visible belt CLI command that sends user input to hosted services. The workflow is intentional, but it still represents external command execution.
Medium
SKILL.md:78-82
Ruby/shell backtick execution
```bash
This range contains a visible belt CLI command that sends user input to hosted services. The workflow is intentional, but it still represents external command execution.
Medium
SKILL.md:88-92
Ruby/shell backtick execution
```bash
This range contains a visible belt CLI command that sends user input to hosted services. The workflow is intentional, but it still represents external command execution.
Medium
SKILL.md:98-108
Ruby/shell backtick execution
```bash
The workflow block runs Tavily search and an OpenRouter Claude model through belt. This is intended, but it executes external commands and sends research data to hosted apps.
Medium
SKILL.md:112-122
Ruby/shell backtick execution
```bash
The workflow block runs extraction and summarization through hosted belt apps. This is intended, but it sends URL content to external services.
Medium
SKILL.md:134-143
Ruby/shell backtick execution
```bash
The related skills block includes npx skills add commands for external skills. These are visible install instructions, but they still create supply-chain exposure if followed.
Medium
SKILL.md:143-145
Ruby/shell backtick execution
```
The range includes an inline belt app store command. It is low impact and visible, but it still encourages use of the external CLI command surface.
Low
SKILL.md:13
Hardcoded URL
![Web Search & Extraction](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgndq
The Markdown image points to a remote cloud.inference.sh asset that may be fetched when rendered. This is visible and low severity, but it is a real external request.

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:4
Broad Belt CLI Permission
The frontmatter grants Bash(belt *), which allows any belt subcommand. This is broader than the documented Tavily and Exa workflows.
The wildcard permission is explicit in the skill frontmatter. The risk is permission breadth rather than hidden malicious intent.
RISK-002 Low
SKILL.md:23SKILL.md:49-60SKILL.md:100-120
Third-Party Research Data Disclosure
The examples submit queries, URLs, search results, and page content to Tavily, Exa, and OpenRouter Claude apps. Users could send confidential material by mistake.
The command examples clearly pass user queries, URLs, and prompts to hosted belt apps. The behavior is documented and aligned with the skill purpose.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    Medium
    Broad belt command permission
    Replace Bash(belt *) with narrower allowed commands for the documented Tavily, Exa, and OpenRouter workflows.
  2. FIX-002
    Medium
    External skill install guidance
    Pin or verify recommended skill install sources and explain the trust boundary before users run npx skills add commands.
  3. FIX-003
    Low
    External service data exposure
    Add a clear warning that queries, URLs, extracted pages, and prompts may be sent to third-party hosted services.

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.

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