CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

30.8 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 1 flagged

Securityscore 88 · 1 finding

MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · SECURITY.md

MEDIUM — it fires on intent; whether the agent honors the non-disclosure imperative depends on the host model.

Why it matters

A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.

The exact value spotted

excerptSECURITY.md· markdown

32- **Protect your session file** (`.session`) — it contains your Telegram authentication. The

… (88 chars elided on L32)

33- Store session files in a secure directory with restricted access

34- Never share session files — they grant full access to your Telegram account

35- Review message content before sending via the MCP server

Occurrences

1 occurrence · at L34

How to fix

Remove the non-disclosure imperative, or rescope it so it limits output format, not honesty to the user.

Delete any "never reveal / never tell the user" line aimed at the model's own behavior.
Keep legitimate confidentiality rules about external data (e.g. "do not echo API keys"), which are user-protective, not user-deceiving.

Framework references

OWASPLLM01 ATLASAML.T0051

Trace & refs

ruleSS-SKILL-INJECT-IMPERATIVE-01sha2561b156a6029264b2c…rubric 365aacaView on GitHub

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/setup-bot/SKILL.md · 1 file

skills/setup-bot/SKILL.md2.7 KB · Markdown

name: setup-bot

description: Diagnose and fix Telegram bot connection issues -- verify config, test send, resolve common errors

argument-hint: "[error message or symptom]"

Setup Bot -- Error Diagnosis

Diagnose and fix Telegram bot connectivity issues. This skill assumes the bot already exists in BotFather -- focus is on getting it working with better-telegram-mcp.

Steps

Verify connection status:

config(action="status") to check current bot token and connection state
If status shows "not configured", the user needs to set TELEGRAM_BOT_TOKEN env var and restart the MCP server (token is NOT runtime-configurable)

Test send to obtain chat_id:

chat(action="list") to see known chats
If no chats appear, instruct user to send any message to the bot first (the bot must receive at least one message to discover chat_id)
Send test: message(action="send", chat_id="<id>", text="Connection test")

Diagnose errors using the flowchart below

Error Diagnosis Flowchart

Send fails
  |
  +-- HTTP 403 "Forbidden: bot was blocked by the user"
  |     -> User blocked the bot. They must unblock it in Telegram.
  |
  +-- HTTP 403 "Forbidden: bot is not a member of the channel/group"
  |     -> Bot not added to the group/channel.
  |     -> For groups: add bot as member via group settings.
  |     -> For channels: add bot as admin (channels require admin for posting).
  |
  +-- HTTP 400 "Bad Request: chat not found"
  |     -> Wrong chat_id format.
  |     -> Groups use negative IDs (e.g., -1001234567890).
  |     -> Channels use negative IDs or @channel_username.
  |     -> Users use positive numeric IDs.
  |
  +-- HTTP 400 "Bad Request: can't parse entities"
  |     -> MarkdownV2 formatting error. See channel-post skill for escaping rules.
  |
  +-- HTTP 401 "Unauthorized"
  |     -> Bot token is invalid or revoked.
  |     -> Verify token with @BotFather (/mybots -> select bot -> API Token).
  |     -> If token was regenerated, update TELEGRAM_BOT_TOKEN and restart.
  |
  +-- HTTP 429 "Too Many Requests"
  |     -> Rate limited. Wait the retry_after seconds indicated in the response.
  |     -> Telegram limits: ~30 messages/second globally, 1 msg/second per chat.
  |
  +-- Connection timeout / DNS resolution failed
  |     -> Network issue. Check internet connectivity.
  |     -> If behind proxy/firewall, Telegram API (api.telegram.org) may be blocked.
  |
  +-- "Not Found" on getMe
        -> Token format is wrong. Must be "123456:ABC-DEF..." format.

When to Use

Bot token is set but messages fail to send
Unclear error messages from Telegram API
Bot works in DM but not in group/channel (or vice versa)
Connection timeouts or auth failures after token rotation

setup-bot— agent skill

Is setup-bot safe to install?

Setup Bot -- Error Diagnosis

Steps

Error Diagnosis Flowchart

When to Use

Audit the pieces. Scan the whole. Decide.