Versioned security assessment

Report ID: SA-181FDEFC

7/23/2026, 9:11:32 AM

nano-banana-edit security assessment v6

Skill Security Certification Report

Audit History
Scanner version 3.0.0 Audit model: codex Latest published report
Skill name
nano-banana-edit
Version
v6
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
skillstore-security-audit-policy-v1

Highest confirmed finding severity

High

2 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.

Most flags are false positives caused by Markdown backticks, placeholder URLs, and a documented token path. The skill still recommends unpinned package execution and sends prompts and image references to RunComfy. Its shell examples do not adequately protect generated user text from shell quoting failures.

Report position

Latest published report

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

Audit attestation

Active attestation

A public attestation is available for this exact report.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 186 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 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 (3)
Medium
SKILL.md:23-25
Ruby/shell backtick execution
```bash
The fenced block contains an unpinned npx command that can download and execute npm code while installing a community skill globally.
Medium
SKILL.md:42-43
Ruby/shell backtick execution
1. **RunComfy CLI** — `npm i -g @runcomfy/cli`
The prerequisite directs users to install an unpinned npm package globally. Package installation can execute lifecycle code with the user's privileges.
Low
SKILL.md:177
Hardcoded URL
The skill invokes `runcomfy run google/nano-banana-2/edit` with a JSON body matching the schema. The
The paragraph explicitly states that the CLI posts requests to the RunComfy API, polls results, and downloads generated files. This is expected functionality but real outbound network activity.

Risk findings

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

Confirmed security concerns (2)

RISK-001 High
SKILL.md:67-74SKILL.md:78-87SKILL.md:91-98SKILL.md:182
Unsafe Shell Boundary for Generated Prompt JSON
The examples place JSON inside a single-quoted shell argument, while the skill states that user prompts enter this argument. CLI-side non-expansion cannot stop shell parsing before the CLI starts.
The documented Bash form has a real quoting boundary, and line 182 confirms user prompt data reaches that argument. Exploitation depends on how the agent constructs and launches the command.
RISK-002 Medium
SKILL.md:53SKILL.md:177SKILL.md:183-184
Third-Party Prompt and Image Disclosure
RunComfy receives the edit prompt and fetches user-provided image URLs. Sensitive images, signed URLs, and prompt content therefore leave the local environment.
The skill explicitly documents public input URLs, API submission, server-side fetching, and outbound service domains.

Remediation

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

  1. FIX-001
    High
    Generated prompt JSON can cross a shell boundary inside a single-quoted argument.
    Invoke the CLI with an argument array and a JSON serializer, or use a protected input file. Never interpolate user text into a shell command.
  2. FIX-002
    Medium
    The installation commands execute unpinned npm packages with global or remote effects.
    Pin reviewed package versions, publish integrity information, and require user confirmation before package installation.
  3. FIX-003
    Medium
    Prompts and image references are transmitted to a third-party model service.
    Require user consent, link the service privacy and retention terms, and warn against sending confidential images or expiring signed URLs.

Expert evidence

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

Artifact subject

Marketplace commit
181fdefcafd96b041926e61c4b2e306ca7e7820e
Content hash
288b68d636f05f603cb84341e9cfcdc37c9ead143ea55c130667591028586d0c
Tree hash
a8ecc5abdda465a8490ab5a278ec86b6187bfab71ea81e177fb463af5dd6f73c
Skill path
skills/agentspace-so/nano-banana-edit
Audit payload hash
522c19e9e2ec0a0e6b059b976ae5938f

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 Signed attestation 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: active