SKILLEMALL.ai
RU Sign in

FF draft-router

(no description)

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: Mark Smith v1.0.0 7 files body ≈ 490 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 33/100 · Will not run — weak spots: steps, result and completion, when it triggers

GeneratorAI and agentstype 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
F
2/100
safety, quality, tests
Safety 60%
4
Quality 40%
0
Run on models
none yet
Process rating
F
33/100
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
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

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.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. Add a description to the frontmatter: without it the skill never triggers.
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 · 4

  • critical Secrets in code secret-telegram-bot drafts-simple.txt:2
    Telegram bot token (quoted — discussed, not commanded)
    var token = "8168…AHl…";
    quoted
  • critical Secrets in code secret-telegram-bot drafts-to-rook.js:6
    Telegram bot token (quoted — discussed, not commanded)
    const ROOK_BOT_TOKEN = '8168…AHl…';
    quoted
Medium and low: 2
  • medium Exfiltration exfil-webhook-url drafts-simple.txt:23
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    var url = "https://api.telegram.org/bot" + token + "/sendMessage";
    quoted
  • low Exfiltration exfil-webhook-url drafts-to-rook.js:32
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    const url = `https://api.telegram.org/bot${ROOK_BOT_TOKEN}/sendMessage`;
    placeholder

Files scanned: 7. 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

Process rating: all ten parameters 33/100

  • 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. 1 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 490 tokens

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
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +4Structure: 7 headings
  • +4Has examples (5 code blocks)

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

External checks

ClawHub: suspicious
The core draft-routing feature is coherent, but the bundle includes hard-coded Telegram credentials and sender scripts that can transmit full draft contents to a fixed external chat without clear user control.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026