Versioned security assessment

Report ID: SA-D46E6208

7/8/2026, 12:23:01 AM

nano-banana-edit security assessment v5

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
nano-banana-edit
Version
v5
Maintainer
agentspace-so
Source
github.com/agentspace-so/runcomfy-agent-skills/tree/main/nano-banana-edit/
Coverage
1 Files scanned · 186 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

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.

Most static findings are false positives caused by Markdown backticks, example URLs, and abbreviated URL placeholders. Confirmed risks include RunComfy CLI execution, global CLI installation, third-party API processing, output downloads, and login side effects. No prompt injection attempt 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 · 186 Lines analyzed

11 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 7 evidence locations

Filesystem access

May read or write local files.

Observed in 4 evidence locations

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 36 evidence locations

Capability review items (10)
Medium
SKILL.md:10
Ruby/shell backtick execution
Calls `runcomfy run google/nano-banana-2/edit` through the local
The skill states it calls the local RunComfy CLI, which is intentional external command execution on the user machine. The command name is fixed, but users must trust the installed CLI and its network behavior.
Medium
SKILL.md:23-25
Ruby/shell backtick execution
```bash
The bash block instructs users to run a global skill installation command from a community GitHub source. This is documented setup guidance, but it is still a real supply-chain and external-command exposure.
Medium
SKILL.md:42-43
Ruby/shell backtick execution
1. **RunComfy CLI** — `npm i -g @runcomfy/cli`
The prerequisite asks users to install the RunComfy CLI globally through npm. Installing and later executing a global CLI is a real external-command and package trust risk.
Medium
SKILL.md:43-44
Ruby/shell backtick execution
2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.
The prerequisite asks users to execute runcomfy login, which starts an authentication flow and changes local credential state. This is expected for the service but remains a real command with security impact.
Medium
SKILL.md:67-74
Ruby/shell backtick execution
```bash
The bash example runs runcomfy run with image URLs and an output directory, causing local command execution and remote API activity. The command is fixed, but it writes outputs and contacts RunComfy.
Medium
SKILL.md:78-87
Ruby/shell backtick execution
```bash
The batch edit example runs the RunComfy CLI against multiple image URLs and writes files to an output directory. This is intended behavior, but it is real external command execution.
Medium
SKILL.md:91-98
Ruby/shell backtick execution
```bash
The targeted edit example invokes runcomfy run with user-selected input data and an output directory. The fixed command limits injection risk, but it still executes a local CLI and performs network work.
Medium
SKILL.md:177
Ruby/shell backtick execution
The skill invokes `runcomfy run google/nano-banana-2/edit` with a JSON body matching the schema. The
The how-it-works section confirms the skill invokes runcomfy, posts to model-api.runcomfy.net, polls, fetches results, and downloads output. This is intentional external command, network, and file-write behavior.
Medium
SKILL.md:181
Ruby/shell backtick execution
- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with m
The security section documents running runcomfy login and persisting an API token. This is expected CLI behavior, but it is still a command with credential side effects.
Medium
SKILL.md:177
Hardcoded URL
The skill invokes `runcomfy run google/nano-banana-2/edit` with a JSON body matching the schema. The
The skill documents posting requests to the RunComfy model API and downloading generated outputs from RunComfy domains. This expected service behavior still transfers user edit data to a third party.

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:177-184
Third-Party Image and Prompt Processing
The skill sends edit prompts and image URL references to the RunComfy model API, and RunComfy fetches user-provided media URLs. Users can expose private creative assets if they provide confidential URLs or prompts.
Lines 177-184 describe posting to RunComfy, downloading outputs, and remote fetching of image URLs. The behavior is disclosed and expected, so this is a privacy risk rather than evidence of malicious exfiltration.

Remediation

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

  1. FIX-001
    Medium
    External CLI execution and global installation are required.
    Recommend a pinned RunComfy CLI version, verify the package source, and ask users to confirm before running install or edit commands.
  2. FIX-002
    Medium
    Prompts and image URL references are processed by RunComfy.
    Add a short privacy warning before examples and advise users not to send confidential assets without approval.
  3. FIX-003
    Low
    RunComfy login stores an API token in the user config directory.
    Document token revocation, avoid logging token values, and prefer RUNCOMFY_TOKEN in controlled CI environments.

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