FC nano-banana-pro
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
As a process C 64/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- 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 · 9
-
critical Secrets in code
secret-openai-key2026-3-10afu的js备份.txt:55OpenAI-style API key (quoted — discussed, not commanded)"apiKey": "sk-J…uwE",
quoted
Medium and low: 8
-
medium Dangerous commands
cmd-execpolicy-bypassAFU_CAPABILITIES.md:231Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File gene…ps1
-
medium Exfiltration
net-credential-useatomic-actions/04-documentation/ATOM-DOC-029-更新飞书原子动作清单.md:67Credential used in a network call (verify the destination is the intended service)$currentContent = Invoke-RestMethod "https://open.feishu.cn/open-apis/docx/v1/documents/$docToken/raw_content"
-
low Secrets in code
secret-high-entropy-token2026-3-10afu的js备份.txt:332High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"appSecret": "t0am…GUe",
quoted -
low Secrets in code
secret-high-entropy-token2026-3-10afu的js备份.txt:334High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"eventSecret": "xi9B…shR",
quoted -
low Secrets in code
secret-high-entropy-token2026-3-10afu的js备份.txt:335High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"verificationToken": "xi9B…shR"
quoted -
low Secrets in code
secret-high-entropy-token2026-3-10afu的js备份.txt:338High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"appSecret": "t0am…GUe",
quoted -
low Secrets in code
secret-high-entropy-token2026-3-10afu的js备份.txt:339High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"verificationToken": "xi9B…shR",
detector -
low Dangerous commands
cmd-background-processAI 数字人教程.md:371Starts a background / autostarted processsudo systemctl enable openclaw
Files scanned: 76. 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 64/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (nano-banana-pro) differs from the folder (playwright-dev)
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 43 steps
- 100Execution cost. Instruction body is 1359 tokens
- 100Running it twice. Mutating operations check current state
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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 183: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 43 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.