Skills/Glama/telegram-mcp

telegram-mcp@1.0.0

CAUTION· install only

Publisher claims: "Connects AI assistants to a Telegram bot so the model can message the user, send files, ask questions and wait for button answers, and read or search chats, groups and forum topics. It also lets the assistant reply as the user in connected personal chats, within the permissions granted in Telegram." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher escolhaperfeitani · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
AUTH_LIMITBOT_TOKENRELAY_TOKENWEBHOOK_PATHConfiguration, not credentials: ALLOWED_USER_IDS, DEV_SKIP_IP_CHECK, FILE_LIMIT, MCP_LIMIT, RETENTION_DAYS
Where it talks to
no vendor host named in the codeAlso t.me, claude.ai, telegram.org, workers.dev, claude.com, chatgpt.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names t.me, claude.ai, telegram.org, workers.dev, claude.com, chatgpt.com as well as its own vendor. The guard injects AUTH_LIMIT, BOT_TOKEN, RELAY_TOKEN, WEBHOOK_PATH only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Credential pass-through configuration; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Privileged sudo commandsrc/relayScript.ts:74 · Privileged sudo command — agent may execute with elevated privilegeselif have dnf; then sudo dnf install -y -q curl jq </dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Credential pass-through configurationsrc/bot/menu.ts:515 · Credential pass-through configuration — agent relays sensitive credentialsconst token = relayToken();Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Privileged sudo commandsrc/relayScript.ts:73 · Privileged sudo command — agent may execute with elevated privilegesif have apt-get; then sudo apt-get update -qq </dev/null && sudo apt-get install -y -qq curl jq </dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Credential pass-through configurationsrc/relay.ts:66 · Credential pass-through configuration — agent relays sensitive credentialsexport const relayToken = () => `relay_${randomId(24)}`;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationsrc/bot/menu.ts:39 · Credential pass-through configuration — agent relays sensitive credentialsimport { fallBack, relayState, relayToken, tokenHash } from "../relay";Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Privileged sudo commandsrc/bot/texts.ts:508 · Privileged sudo command — agent may execute with elevated privileges"<code>claude</code>, затем /login, затем <code>sudo systemctl restart tg-relay</code>. В команде токен " +Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/bot/texts.ts:237 · Privileged sudo command — agent may execute with elevated privileges"<code>claude</code>, then /login, then <code>sudo systemctl restart tg-relay</code>. This command holds the " +Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/bot/texts.ts:501 · Privileged sudo command — agent may execute with elevated privileges"⚠️ Слетел вход в Claude. На машине: <code>claude</code>, затем /login, затем <code>sudo systemctl restart tg-relay</code>.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/bot/texts.ts:230 · Privileged sudo command — agent may execute with elevated privileges"⚠️ Its Claude sign-in expired. On the machine: <code>claude</code>, then /login, then <code>sudo systemctl restart tg-relay</code>.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Credential pass-through configurationsrc/relay.ts:178 · Credential pass-through configuration — agent relays sensitive credentialsif (!relay) return new Response("unknown relay token\n", { status: 401 });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Privileged sudo commandsrc/bot/texts.ts:241 · Privileged sudo command — agent may execute with elevated privileges"⚠️ The relay's Claude sign-in expired, so replies to sessions start new sessions instead. On the machine: <code>claude</code>, then /login, then <code>sudo systemctl restart tg-relay</code>.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:38 · Collapsed <details> block carrying instructions<summary>Or from a terminal</summary> ```bash bun install ``` ```bash bunx wrangler login ``` ```bash bun run deploy ``` ```bash bunx wrangler secret put BOT_TOFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Pipe-to-shell patternsrc/relayScript.ts:79 · Pipe-to-shell pattern — downloads and immediately executes remote codeif ! have claude; then curl -fsSL https://claude.ai/install.sh | bash </dev/null; fiFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Access to sensitive file pathstest/sessions.test.ts:39 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst result = await h.tool(alice, "send_message", { text: "x", session: "../etc/passwd" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandsrc/relayScript.ts:75 · Privileged sudo command — agent may execute with elevated privilegeselif have yum; then sudo yum install -y -q curl jq </dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontest/business.test.ts:424 · File type combined with upload action — agent may exfiltrate local data filesfile: { filename: "a.txt", text: "a", upload: true },Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Credential pass-through configurationtest/relay.test.ts:41 · Credential pass-through configuration — agent relays sensitive credentialsasync function relayToken(): Promise<string> {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Privileged sudo commandsrc/relayScript.ts:90 · Privileged sudo command — agent may execute with elevated privilegessudo tee /etc/systemd/system/tg-relay.service >/dev/null <<UNITFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontest/business.test.ts:162 · File type combined with upload action — agent may exfiltrate local data files{ chat: "Anna", file: { filename: "a.txt", upload: true } },Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontest/business.test.ts:436 · File type combined with upload action — agent may exfiltrate local data filesfile: { filename: "a.txt", upload: true },Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/store.ts:2186 · File type combined with upload action — agent may exfiltrate local data filesthis.db.prepare("DELETE FROM upload_nonces WHERE expires_at < ?").bind(nowSeconds()),Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellsrc/relayScript.ts:79 · Remote installer piped to shellif ! have claude; then curl -fsSL https://claude.ai/install.sh | bash </dev/null; fiFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Credential pass-through configurationtest/relay.test.ts:98 · Credential pass-through configuration — agent relays sensitive credentialsawait relayToken();Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
LOW
Authorization escalation languageREADME.md:99 · Authorization escalation language · informational: not an instruction file**ChatGPT** (needs Developer mode: Pro, Business, Enterprise, Edu): Settings → Apps & Connectors →Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageREADME.md:100 · Authorization escalation language · informational: not an instruction fileAdvanced → Developer mode on, then **Create** with the same URL and **OAuth** authentication.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:100 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileAdvanced → Developer mode on, then **Create** with the same URL and **OAuth** authentication.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Hidden zero-width characters detectedsrc/tools/edit.ts:236 · Hidden zero-width characters detected — may conceal content… 😱 🎉 🤩 🙏 👌 🕊 🤡 🥱 😍 🐳 💯 🤣 ⚡ 🏆 💔 🤨 😐 🍓 🍾 💋 🖕 😈 😴 😭 🤓 👻 👨‍💻 👀 🎃 🙈 😇 😨 🤝 ✍ 🤗 🫡 🎅 🎄 ☃ 💅 🤪 🗿 🆒 💘 🙉 🦄 😘 💊 🙊 😎 👾 🤷 😡. …Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commandsrc/relayScript.ts:88 · File permission modification command — agent changes file ownership/permissionschmod 700 "$DIR/relay.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Prompt injectionREADME.md:99 · Prompt injection — known jailbreak technique reference · informational: not an instruction file**ChatGPT** (needs Developer mode: Pro, Business, Enterprise, Edu): Settings → Apps & Connectors →Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actiontest/business.test.ts:178 · File type combined with upload action — agent may exfiltrate local data files["create_upload_url", { chat: "Anna", filename: "a.txt" }, "send_as_user"],Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontest/business.test.ts:177 · File type combined with upload action — agent may exfiltrate local data files["send_file", { chat: "Anna", filename: "a.txt", text: "x" }, "send_as_user"],Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Credential pass-through configurationtest/relay.test.ts:127 · Credential pass-through configuration — agent relays sensitive credentialsconst token = await relayToken();Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
File permission modification commandsrc/relayScript.ts:83 · File permission modification command — agent changes file ownership/permissionsmkdir -p "$DIR" && chmod 700 "$DIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/relayScript.ts:85 · File permission modification command — agent changes file ownership/permissionschmod 600 "$DIR/env"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Credential pass-through configurationtest/relay.test.ts:82 · Credential pass-through configuration — agent relays sensitive credentialsconst token = await relayToken();Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Credential pass-through configurationtest/relay.test.ts:105 · Credential pass-through configuration — agent relays sensitive credentialsconst token = await relayToken();Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02

Cost to the agent

Instructions loaded
≈425 tok
2 files · 63 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim escolhaperfeitani: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim escolhaperfeitaniPropose a patch to the maintainer