SKILLEMALL.ai
GitHub ↗ RU Sign in

CB shark

(no description)

ClawHub Agent Skills author: keugenek v0.1.0 MIT-0 16 files · 1 script body ≈ 5 280 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 68/100 · Nearly there — weak spots: inputs and preconditions

ReferenceInfrastructuretype 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
64/100
safety, quality, tests
Safety 60%
89
Quality 40%
26
Run on models
none yet
Process rating
B
68/100
Nearly there
Inputs and preconditions w 11
0
When it triggers w 12
50
Tools and files w 18
60
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.

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Add a description to the frontmatter: without it the skill never triggers.
  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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-execpolicy-bypass commands/shark-loop.md:23
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File "$SKILL_DIR/shark.ps1" "<TASK_DESCRIPTION>"
  • medium Dangerous commands cmd-execpolicy-bypass SKILL.md:547
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File "<skill_dir>/shark.ps1" "<task>"
  • low Dangerous commands cmd-execpolicy-bypass commands/shark-loop.md:4
    Runs PowerShell with execution policy bypassed (detector / deny-list definition)
    allowed-tools: ["Bash(powershell.exe -ExecutionPolicy Bypass -File:*)"]
    detector

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-missing SKILL.md: no `description` — the skill can never trigger
  • warning body-long SKILL.md body ≈ 5280 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 68/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 50When it triggers. States when to use, but not when not to
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 5280 tokens
  • 100Steps. 126 steps
  • 100Failures and branches. 10 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 21 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 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)
  • +3Description length 0: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +4Structure: 60 headings
  • +3Step-by-step instructions: 126 items
  • +3Output format is stated explicitly
  • +4Has examples (27 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 26.

External checks

ClawHub: suspicious
This is a coherent performance skill, but it gives agents broad background execution authority and includes a loop that bypasses normal Claude permission checks.
LLM: suspicious (high) · VirusTotal: · 29 May 2026