Versioned security assessment

Report ID: SA-D71C7417

7/12/2026, 9:56:19 AM

ai-video-generation security assessment v4

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
ai-video-generation
Version
v4
Maintainer
101-skills
Source
github.com/101-skills/skills/tree/main/tools/video/ai-video-generation/
Coverage
1 Files scanned · 253 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.

The Ruby backtick alerts are Markdown formatting false positives, while one remote image reference can trigger a low-risk external request. Semantic review found broad belt command authorization and undisclosed third-party processing of user media. No prompt injection or malicious intent 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 · 253 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

    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 19 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 50 evidence locations

Capability review items (1)
Low
SKILL.md:13
Hardcoded URL
![AI Video Generation](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kg2c0egyg
This Markdown image references cloud.inference.sh and may be fetched when the document renders. That external request can disclose viewer network metadata to the host.

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 Command Authorization
The Bash allowlist permits every belt subcommand, while the documented workflow only needs login, app discovery, and app execution operations.
The frontmatter explicitly grants Bash(belt *), which is broader than the specific subcommands shown later. The excess scope is directly observable.
RISK-002 Medium
SKILL.md:108-120
External Processing of User Media
Examples send portrait, audio, image, and video locations to third-party inference applications without a privacy or consent warning.
The examples pass image and audio URLs to remote app runs. The reviewed skill contains no nearby disclosure about external processing or sensitive media.

Remediation

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

  1. FIX-001
    Medium
    The Bash allowlist grants all belt subcommands.
    Restrict authorization to the required belt subcommands where supported, and require confirmation for login or other account-changing operations.
  2. FIX-002
    Medium
    Media examples send user assets to external inference providers without a privacy warning.
    State that inputs are processed externally and require users to confirm rights, consent, sensitivity, and provider policies before submission.
  3. FIX-003
    Low
    The skill embeds an externally hosted image that may load during rendering.
    Bundle the image with the skill or use a marketplace-hosted asset to avoid unintended third-party requests.

Expert evidence

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

Artifact subject

Marketplace commit
d71c7417a35d5c2624161bd2fe8de8a41a362128
Content hash
2133bff3a2698f0a1409994a299fd94cf658d56c17322f9a0453ad1ef3cbb531
Tree hash
eed05eb86acf119032e90d7d43c271bad6002415deb8e2221c1d69e7e8c358b4
Skill path
skills/101-skills/ai-video-generation
Audit payload hash
ac63ad5d8e2cce2dd9ede735e00d05ea

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