Skills/PyPI/nanobanana-pro-mcp-server

nanobanana-pro-mcp-server@1.0.1

CAUTION· not started

Publisher claims: "A production-ready MCP server for AI-powered image generation using Gemini 3 Pro Image (Nano Banana Pro) and Gemini 2.5 Flash Image with intelligent model selection" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher qso · publishing for 296 daysInstalls 26Last detonated 38 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
API_KEYAPI_KEY_LENGTHGEMINI_API_KEYGOOGLE_API_KEYNANOBANANA_AUTH_METHODConfiguration, not credentials: FASTMCP_HOST, FASTMCP_MASK_ERRORS, FASTMCP_PORT, FASTMCP_TRANSPORT, GCP_PROJECT_ID, GCP_REGION, GOOGLE_CLOUD_LOCATION, GOOGLE_CLOUD_PROJECT, IMAGE_OUTPUT_DIR, LOG_FORMAT, NANOBANANA_MODEL, PYTHON_PATH, VENV_PYTHON_PATH
Where it talks to
no vendor host named in the codeAlso astral.sh, google.dev, google.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names astral.sh, google.dev, google.com as well as its own vendor. The guard injects API_KEY, API_KEY_LENGTH, GEMINI_API_KEY, GOOGLE_API_KEY, NANOBANANA_AUTH_METHOD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx nanobanana-pro-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/build.py:18 · Python subprocess execution detectedresult = subprocess.run(cmd, check=True, capture_output=capture_output, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsCLAUDE.md:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescp .env.example .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/build.py:58 · Python subprocess execution detectedsubprocess.run(["uv", "--version"], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsCLAUDE.md:114 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Loads from `.env` file or environment variablesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternscripts/build.py:70 · Pipe-to-shell pattern — downloads and immediately executes remote codeprint(" curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsCLAUDE.md:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Edit .env to add your GEMINI_API_KEYFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternscripts/setup-cursor.sh:35 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellscripts/build.py:70 · Remote installer piped to shellprint(" curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
CRITICAL
Pipe-to-shell patternscripts/upload.py:41 · Pipe-to-shell pattern — downloads and immediately executes remote codeprint(" curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsCLAUDE.md:129 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files2. `.env` file valuesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hidden zero-width characters detectednanobanana_mcp_server/tools/generate_image.py:373 · Hidden zero-width characters detected — may conceal contentextra_info += f" • 👨‍👩‍👧 Parent: {meta.get('parent_file_id')}"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedscripts/upload.py:37 · Python subprocess execution detectedsubprocess.run(["uv", "--version"], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/upload.py:158 · Python subprocess execution detectedcheck_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellscripts/upload.py:41 · Remote installer piped to shellprint(" curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedscripts/build.py:75 · Python subprocess execution detectedsubprocess.run(["uv", "run", "python", "-c", "import build"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/cleanup-ports.sh:16 · Process kill command — agent can terminate processes# Check specific ports and kill processes using themFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/cleanup-ports.sh:21 · Process kill command — agent can terminate processeskill $pid 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/upload.py:51 · Python subprocess execution detectedresult = subprocess.run(["uv", "add", "--dev", "twine"], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/upload.py:20 · Python subprocess execution detectedresult = subprocess.run(cmd, check=True, capture_output=capture_output, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellscripts/setup-cursor.sh:35 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedscripts/upload.py:46 · Python subprocess execution detectedsubprocess.run(["uv", "run", "python", "-c", "import twine"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈3,400 tok
2 files · 71 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for nanobanana-pro-mcp-server@1.0.1 as of 38 h ago. This is the package itself, not its dependencies.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim qso: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim qsoPropose a patch to the maintainer