Versioned security assessment

Report ID: SA-E397CE5A

7/6/2026, 8:34:13 PM

fun-brainstorming security assessment v3

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
fun-brainstorming
Version
v3
Maintainer
roin-orca
Source
github.com/roin-orca/skills/tree/main/skills/fun-brainstorming/
Coverage
1 Files scanned · 57 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

High

1 confirmed security finding requires 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 opening bash block is a real external command risk because it runs a global npx installer from a community repository. The other two static findings are false positives from Markdown and DOT code fences. A high-risk prompt-style instruction also tries to force command execution before normal use.

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 · 57 Lines analyzed

2 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.

Not recorded by this audit

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 3 evidence locations

Capability review items (1)
High
SKILL.md:8-10
Ruby/shell backtick execution
```bash
The fenced bash block instructs the agent to run npx skills add from a community repository with --yes and -g before use. This can execute untrusted package code and modify global tooling without explicit user approval.

Risk findings

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

Confirmed security concerns (1)

RISK-001 High
SKILL.md:6-10
Prompt Injection Attempt Detected
The skill says "FIRST AND FOREMOST YOU MUST RUN THIS TO CHECK FOR UPDATES" before an npx installer command. This attempts to make the assistant execute untrusted setup steps before normal analysis.
The imperative text is directed at the assistant and is paired with a command that installs from a community repository using --yes and global flags.

Remediation

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

  1. FIX-001
    High
    Mandatory external installer command
    Remove the opening npx command from SKILL.md. Do not require automatic global installs or --yes execution during skill loading.
  2. FIX-002
    High
    Prompt-style imperative wording
    Replace language that tells the assistant it must run commands with neutral setup guidance for human users.
  3. FIX-003
    Medium
    Untrusted update flow
    Document optional update steps outside the runtime skill text. Require explicit user consent, pinned versions, and no global install by default.

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