SKILLEMALL.ai
GitHub ↗ RU Sign in

CF hubstudio-openapi

HubStudio OpenAPI skill for full endpoint lookup, request/response field explanation, and parameter constraint checking. Use when querying HubStudio API interfaces, validating request payloads, or building automation against openapi.yaml.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: hubstudio-Max v1.0.0 MIT-0 12 files body ≈ 1 854 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 46/100 · Will not run — References files that are not bundled: scripts/endpoint_test_report.json, scripts/validate_completeness.py

IntegrationInfrastructuretype 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
C
74/100
safety, quality, tests
Safety 60%
73
Quality 40%
76
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: scripts/endpoint_test_report.json, scripts/validate_completeness.py
Tools and files w 18
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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.

Exfiltration
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The text references files that are not there: add them or drop the references.
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 · 10

  • high Exfiltration intent-browser-credential-store skill-card.md:20
    Accesses a browser credential / cookie store
    Risk: The skill can give an agent broad control over HubStudio browsers, cloud phones, cookies, accounts, files, and local API operations. <br>
Medium and low: 9
  • low Secrets in code secret-high-entropy-token commands.generated.json:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "command": "post…ist",
    quoted
  • low Secrets in code secret-high-entropy-token commands.generated.json:29
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "command": "post…ate",
    quoted
  • low Secrets in code secret-high-entropy-token commands.generated.json:91
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "command": "post…all",
    quoted
  • low Secrets in code secret-high-entropy-token commands.generated.json:139
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "command": "post…ist",
    quoted
  • low Secrets in code secret-high-entropy-token commands.generated.json:168
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "command": "post…ile",
    quoted
  • low Secrets in code secret-high-entropy-token hubstudio.js:16
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    browserStatus: "post…tus",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:18
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…uWm+fFRcIOgKBMiOBP+eXiy…9ab+DDKA==",
    detector
  • low Secrets in code secret-high-entropy-token SKILL.md:140
    High-entropy token-like string (may be an id, hash or a credential)
    node hubstudio.js post…Adb --body '{"mobileIds":["<mobileId>"],"enableAdb":true}'
  • low Secrets in code secret-high-entropy-token SKILL.md:299
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    2. Enable ADB via `post…Adb`
    quoted

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/endpoint_test_report.json
  • warning missing-ref reference to a missing file: scripts/validate_completeness.py

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: scripts/endpoint_test_report.json, scripts/validate_completeness.py
  • 0Tools and files. 2 referenced file(s) missing: scripts/endpoint_test_report.json, scripts/validate_completeness.py
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (hubstudio-openapi) differs from the folder (hubstudio)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 59 steps
  • 100Execution cost. Instruction body is 1854 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress
  • low 11 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)
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 238: enough signal without eating the budget
  • +4Structure: 37 headings
  • +3Step-by-step instructions: 59 items
  • +3Output format is stated explicitly
  • +4Has examples (16 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
This skill is openly a HubStudio automation wrapper, but it gives agents broad control over browsers, cloud phones, cookies, accounts, files, and shell execution without enough scoping or confirmation safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026