Versioned security assessment

Report ID: SA-D71C7417

7/12/2026, 9:52:20 AM

ai-image-generation security assessment v5

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
ai-image-generation
Version
v5
Maintainer
101-skills
Source
github.com/101-skills/skills/tree/main/tools/image/ai-image-generation/
Coverage
1 Files scanned · 172 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

3 confirmed security findings require attention.

Installation context

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

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

The scanner mostly mistook Markdown formatting and model identifiers for Ruby or shell backtick execution. A remote image, mutable installation guidance, broad belt permission, and hosted processing create low-to-medium privacy and supply-chain risks. No prompt injection or malicious exfiltration intent was found.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

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 · 172 Lines analyzed

5 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

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  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 44 evidence locations

Capability review items (2)
Low
SKILL.md:13
Hardcoded URL
![AI Image Generation](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kg0v0nz7w
The remote Markdown image may be fetched automatically when rendered, exposing viewer network metadata and allowing the hosted content to change.
Low
SKILL.md:17
Hardcoded URL
> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer
The installation link targets mutable raw content on a remote repository. Following changing installation instructions creates a limited supply-chain risk.

Risk findings

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

Confirmed security concerns (3)

RISK-001 Medium
SKILL.md:4
Broad belt CLI Permission
The allowed-tools rule permits every belt subcommand, while the documented workflow needs only login, app discovery, and app execution.
The wildcard permission is explicit and broader than the commands demonstrated in the file. The impact depends on capabilities exposed by the installed belt CLI.
RISK-002 Medium
SKILL.md:7SKILL.md:17SKILL.md:140-161
Unpinned Third-Party Skill Installation
The skill recommends unversioned npx installations and mutable remote instructions, so later upstream changes may alter installed behavior without review.
The commands and raw repository link contain no immutable version or commit pin. This is a clear supply-chain exposure, although no malicious upstream behavior is shown.
RISK-003 Medium
SKILL.md:58-70SKILL.md:123-124SKILL.md:129-133
Prompts and Image References Sent to Hosted Models
The examples submit prompts and user-supplied image URLs to hosted model applications, which may expose sensitive creative or personal data.
The app-run examples explicitly include prompts and external image URLs as inputs. Service-side retention and access controls are not described in the skill.

Remediation

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

  1. FIX-001
    Medium
    The allowed-tools rule grants access to every belt subcommand.
    Restrict permission to the belt subcommands required for login, app discovery, and app execution.
  2. FIX-002
    Medium
    Installation commands and raw instructions are not pinned to immutable versions.
    Pin skill dependencies and installation documentation to reviewed releases or commit hashes.
  3. FIX-003
    Medium
    Prompts and image URLs may contain sensitive information sent to hosted providers.
    Add a clear data-handling warning and advise users to avoid confidential images, prompts, and private URLs.
  4. FIX-004
    Low
    The introduction embeds an externally hosted image.
    Bundle a reviewed local image asset or document that rendering the file may contact the remote host.

Expert evidence

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

Artifact subject

Marketplace commit
d71c7417a35d5c2624161bd2fe8de8a41a362128
Content hash
1570d6d46798e4cf7acc3e61e1f10bbd0aaa9bf3fb0e1d2a96f10fbc5f9cdd49
Tree hash
6432408ae81bec8740b86cb1ccc51efbb606d98fbecf3565805cc7397fca3468
Skill path
skills/101-skills/ai-image-generation
Audit payload hash
876959b0ce1d2621c8cdceb7236246d0

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 Source

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

Audit attestation: not_attestable