SKILLEMALL.ai
GitHub ↗ RU Sign in

BC telethon-plus

HTTP + MCP control plane over a REAL Telegram MTProto userbot (Telethon) — a full user account, not the Bot API. Send/read/edit/delete/forward messages, browse dialogs, resolve entities/contacts, download + send media, manage chats (create/join/leave/admin), run polls, and forward every incoming message to a webhook (TELETHON_POST_TO_URL). JSON in / JSON out on one port; MCP streamable-HTTP at /mcp/ mirrors the same tools; optional bearer auth. Built-in anti-flood throttling keeps the account under Telegram's limits. Use when the user wants an agent, script, or curl one-liner to drive their own Telegram account over HTTP/MCP — read a chat, DM someone, post to a channel, react/pin, or pipe incoming DMs into an app. Drives a real account acting AS the user with full account access.

ClawHub Agent Skills author: Ciprian Mandache v0.5.7 MIT-0 4 files · 1 script body ≈ 6 325 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

HTTP + MCP control plane over a REAL Telegram MTProto userbot (Telethon) — a full user account, not the Bot API.

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationTelegramDockerAI 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
B
87/100
safety, quality, tests
Safety 60%
93
Quality 40%
77
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.
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 net-credential-use SKILL.md:454
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $TELETHON_AUTH_KEY" $TELETHON_PLUS_URL/api/me | jq
  • low Exfiltration read-dotenv references/setup.md:27
    Reads a .env file
    cp .env.example .env
  • low Risky intent intent-offensive-security SKILL.md:345
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | `promote` | `user`, `title?` (≤16 chars), plus booleans `change_info`, `post_messages`, `edit_messages`, `delete_messages`, `ban_users`, `invite_users`, `pin_messages`, `add_admins`, `anonymous`, `m

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6325 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 59/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 57 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Failures and branches. 2 branches
  • 70Execution cost. Instruction body is 6325 tokens
  • 100Steps. 35 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 28 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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 790: enough signal without eating the budget
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 35 items
  • +4Has examples (29 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: clean
This skill is a powerful Telegram account control tool, but its high-impact access and risks are clearly disclosed and aligned with its purpose.
LLM: benign (high) · VirusTotal: · 1 Aug 2026