SKILLEMALL.ai
GitHub ↗ RU Sign in

BC newapi

Assistant for newapi (new-api), an open-source unified AI gateway platform (https://github.com/QuantumNous/new-api). Use when the user asks about New API, managing models, groups, balance, or tokens, or securely copying keys, applying them to config files, or using them in commands without exposing secrets.

ClawHub Agent Skills author: Calcium-Ion v0.1.1 MIT-0 15 files body ≈ 986 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationGitHubInfrastructuretype 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
B
85/100
safety, quality, tests
Safety 60%
88
Quality 40%
81
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
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.

Exfiltration 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 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".

For the author

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

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Exfiltration net-redirectable-api-key scripts/env.js:59
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-credential-use scripts/fetch-key.js:13
      Credential used in a network call (verify the destination is the intended service)
      const res = await fetch(`${baseUrl}/api/token/${tokenId}/key`, {
    • low Secrets in code secret-password-literal docs/actions-config.md:51
      Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)
      - YAML: `apiKey: __NE…2__`
      quoted
    • low Secrets in code secret-password-literal docs/actions-config.md:53
      Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)
      - TOML: `api_key = "__NE…2__"`
      quoted

    Files scanned: 15. 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 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Failures and branches. 2 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 11 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 986 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low The response is described with custom markup (11 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)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • -33 of 7 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 308: enough signal without eating the budget
    • +4Structure: 5 headings
    • +3Step-by-step instructions: 11 items
    • +4Reference files are cited in the instructions (6 of 6)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

    External checks

    ClawHub: suspicious
    The skill is purpose-built for NewAPI management, but it gives the agent sensitive token-management power and includes an under-contained command execution path.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026