SKILLEMALL.ai
RU Sign in

BC nova-app-builder

Build and deploy Nova Platform apps (TEE apps on Sparsity Nova / sparsity.cloud). Use when a user wants to create a Nova app, write enclave application code, build it into a Docker image, and deploy it to the Nova Platform to get a live running URL. Handles the full lifecycle: scaffold, code, build, push, deploy, verify running. Triggers on requests like 'build me a Nova app', 'deploy to Nova Platform', 'create a TEE app on sparsity.cloud', 'I want to run an enclave app on Nova'.

ClawHub Agent Skills author: Zhengfa Dang v2.3.1 MIT-0 11 files body ≈ 6 882 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice

GeneratorDockerGitHubInfrastructuretype 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
84/100
safety, quality, tests
Safety 60%
88
Quality 40%
79
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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-credential-use SKILL.md:337
    Credential used in a network call (verify the destination is the intended service)
    RESP=$(curl -s "$BASE/deployments/$DEPLOY_ID/status" -H "Authorization: Bearer $TOKEN")
  • medium Exfiltration net-credential-use SKILL.md:346
    Credential used in a network call (verify the destination is the intended service)
    curl -s "$BASE/apps/$SQID/detail" -H "Authorization: Bearer $TOKEN" \
  • low Secrets in code secret-high-entropy-token references/nova-api.md:90
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | `nova_app_registry` | string | **Required if KMS** | Registry contract: `0x0f…cc8` |
    table
  • low Secrets in code secret-high-entropy-token references/nova-api.md:184
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "nova_app_registry": "0x0f…cc8",
    quoted

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6882 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 59/100

  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 32 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6882 tokens
  • 100Steps. 77 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill

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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 484: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 77 items
  • +4Has examples (14 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: clean
This is a disclosed Nova app build/deploy helper, but users should handle the GitHub and Nova credentials carefully.
LLM: benign (high) · VirusTotal: benign · 28 May 2026