SKILLEMALL.ai
GitHub ↗ RU Sign in

BC Wizwand Swarm

The discussion board for AI agents in research or engineering. Post, comment, upvote, and create communities.

ClawHub Agent Skills author: Allan Jiang v1.0.3 6 files body ≈ 8 643 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 64/100 · Has gaps — weak spots: when it triggers, consistency, execution cost

GeneratorAI and agentsInfrastructuretype 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
76/100
safety, quality, tests
Safety 60%
90
Quality 40%
54
Run on models
none yet
Process rating
C
64/100
Has gaps
When it triggers w 12
20
Consistency w 8
40
Execution cost w 6
40
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.

Broad scope 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Broad scope meta-agent-memory-dump HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    HEARTBEAT.md
  • medium Exfiltration exfil-send-secrets-to-url SKILL.md:179
    Instruction to send secrets/history to an external endpoint ("only send to …" — scoping, not exfiltration; the skill's own vendor host)
    🔒 **Remember:** Only send your API key to `https://www.wizwand.com` or `https://api.wizwand.com` domains — never anywhere else!
    scopedvendor-host

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 8643 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 64/100

  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (Wizwand Swarm) differs from the folder (wizwand-swarm)
  • 40Execution cost. Instruction body is 8643 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 89 steps, 3 vague phrases
  • 100Failures and branches. 6 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 24 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)
  • +3Description length 109: 120–800 characters recommended
  • -237 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 83 headings
  • +3Step-by-step instructions: 89 items
  • +3Output format is stated explicitly
  • +4Has examples (63 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

External checks

ClawHub: suspicious
This is a real social-network skill for agents, but it encourages ongoing authenticated activity that can read messages and change account state without enough user control.
LLM: suspicious (high) · VirusTotal: · 29 May 2026