SKILLEMALL.ai
GitHub ↗ RU Sign in

AB nano-banana-2

Gemini image generation, editing, and search-grounded image creation via gemini-3.1-flash-image-preview (Nano Banana 2). USE FOR: - Generating images from text prompts (text-to-image) - Editing or transforming an existing image with text instructions - Generating images grounded in live web/image search results Requires GEMINI_API_KEY environment variable. See rules/setup.md for configuration and rules/security.md for output handling guidelines.

ClawHub Agent Skills author: frank-bot07 v0.1.0 4 files body ≈ 2 516 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 68/100 · Nearly there — weak spots: when it triggers, consistency, running it twice

GeneratorWriting and documentsAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
93
Quality 40%
91
Run on models
none yet
Process rating
B
68/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash(curl *)
      allowed-tools: Bash(curl *) Bash(python3 *) Bash(mkdir *) Bash(open .nano-banana/*)
    • low Dangerous commands cmd-shell-rc rules/setup.md:25
      Writes to a shell startup file (documentation of a security skill)
      echo 'export GEMINI_API_KEY="your-key-here"' >> ~/.zshrc
      security skill
    • low Exfiltration read-dotenv rules/setup.md:40
      Reads a .env file (documentation of a security skill)
      source .env
      security skill

    Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 68/100

    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 3 mutating operations with no state check
    • 40Consistency. Frontmatter name (nano-banana-2) differs from the folder (nano-banana-2-gemini)
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 75Steps. 3 steps
    • 100Tools and files. Tools declared in frontmatter
    • 100Failures and branches. 2 branches, has a failure section
    • 100Execution cost. Instruction body is 2516 tokens

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +3Description length 451: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 3 items
    • +3Output format is stated explicitly
    • +4Has examples (9 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    The skill does what it claims, but its setup instructions can expose the full Gemini API key in command output.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026