SKILLEMALL.ai
GitHub ↗ RU Sign in

CD openclaw-vmake-ai

Process image or video watermark removal and quality restoration with Vmake AI. Always discover the remote catalog before naming or selecting a task: V2 uses the returned server task metadata; legacy aliases are allowed only when the legacy config explicitly returns them. Video tasks use spawn-run-task plus OpenClaw sessions_spawn; image tasks use blocking run-task. Paid API (consumes tenant quota); never claim the service is free or invent pricing.

ClawHub Agent Skills author: wemayiiii v2.0.0 MIT-0 44 files · 33 scripts body ≈ 7 410 tokens Open the sourceclawhub.ai↗ analyzed 9 d ago

Process image or video watermark removal and quality restoration with Vmake AI.

As a process D 44/100 · Unfinished process — References files that are not bundled: scripts/.env

ProcedureTelegramMedia and videotype 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
82/100
safety, quality, tests
Safety 60%
93
Quality 40%
65
Run on models
none yet
Process rating
D
44/100
Unfinished process
References files that are not bundled: scripts/.env
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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.
  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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Exfiltration exfil-webhook-url scripts/vmake_ai.py:999
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    f"https://api.telegram.org/bot{token}/getFile",
    quoted
  • low Dangerous commands cmd-eval-dynamic scripts/test_agent_info.py:74
    Dynamic code execution from decoded/untrusted input (test fixture / example file)
    exec(compile(ast.Module(body=[node], type_ignores=[]), "client.py", "exec"), env)
    fixture
  • low Exfiltration read-dotenv SKILL.md:151
    Reads a .env file
    source scripts/.env

Files scanned: 43. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7410 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/.env
  • note edit-residue the text marks something as outdated (lines 55, 56, 70, 86, 157, 204): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: scripts/.env
  • 0Tools and files. 1 referenced file(s) missing: scripts/.env
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (openclaw-vmake-ai) differs from the folder (vmake-skill)
  • 60Steps. 51 steps, 4 vague phrases
  • 70Execution cost. Instruction body is 7410 tokens
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 9 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -34 of 10 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 453: enough signal without eating the budget
  • +4Structure: 28 headings
  • +3Step-by-step instructions: 51 items
  • +4Has examples (19 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: suspicious
The skill is a coherent Vmake media-processing integration, but it needs review because it relays arbitrary server messages and links and uses under-scoped network/download paths for user media and service endpoints.
LLM: suspicious (high) · 14 Sept 2026