SKILLEMALL.ai
GitHub ↗ RU Sign in

DF pieces-mcp

(no description)

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Jack Ross v1.0.3 MIT-0 2 files body ≈ 5 316 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 24/100 · Will not run — weak spots: steps, result and completion, when it triggers

ReferenceAI 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
D
40/100
safety, quality, tests
Safety 60%
66
Quality 40%
0
Run on models
none yet
Process rating
F
24/100
Will not run
Steps w 15
0
Result and completion w 14
0
When it triggers w 12
0
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. Add a description to the frontmatter: without it the skill never triggers.
  3. 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 · 5

  • high Exfiltration exfil-webhook-url SKILL.md:112
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    https://SOMETHING.ngrok-free.dev
Medium and low: 4
  • medium Exfiltration exfil-webhook-url SKILL.md:97
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    > `https://SOMETHING.ngrok-free.dev -> http://loca…300`
    quoted
  • medium Exfiltration exfil-webhook-url SKILL.md:456
    Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition)
    "https://SOMETHING.ngrok-free.dev/model_context_protocol/2025-03-26/mcp"
    detector
  • medium Exfiltration exfil-webhook-url SKILL.md:630
    Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row)
    | **ngrok** | `https://abc1…dev` | Most common; may require auth setup |
    table
  • low Exfiltration exfil-webhook-url SKILL.md:39
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - `https://...ngrok-free.dev`
    placeholder

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error frontmatter SKILL.md: no YAML frontmatter block found
  • error name-missing SKILL.md: frontmatter has no `name`
  • error description-missing SKILL.md: no `description` — the skill can never trigger
  • warning body-long SKILL.md body ≈ 5316 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 24/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 5 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5316 tokens
  • 100Consistency. Name and required fields are in place
  • 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
  • +4Structure: 2 headings, hard to scan
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Has examples (36 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

External checks

ClawHub: suspicious
This skill appears purpose-aligned, but it gives OpenClaw persistent read/write access to a tunneled long-term memory service with too few user-control safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026