telegram-agent-mcp@0.5.0
CAUTION· install onlyPublisher claims: "MCP server exposing a Telegram bot so LLM agents can converse, discover each other, and route tasks in a shared group chat" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
TELEGRAM_AGENT_1_TOKENTELEGRAM_BOT_TOKENConfiguration, not credentials: TELEGRAM_AGENT_DESCRIPTION, TELEGRAM_AGENT_MODEL, TELEGRAM_AGENT_NAME, TELEGRAM_AGENTS_FILE, TELEGRAM_IDLE_SHUTDOWN_SECS, TELEGRAM_MCP_HTTP_ADDR, TELEGRAM_PRIMARY_AGENT- Where it talks to
- no vendor host named in the codeAlso telegram.org — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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 telegram.org as well as its own vendor. The guard injects TELEGRAM_AGENT_1_TOKEN, TELEGRAM_BOT_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-19 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
curl -s $hdr -D h_x.txt -o /dev/null -X POST "http://127.0.0.1:8787/mcp?agent=nope" -d "$init"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.curl -s $hdr -D h_a.txt -o /dev/null -X POST "http://127.0.0.1:8787/mcp?agent=alpha" -d "$init"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.curl -s $hdr -D h_b.txt -o /dev/null -X POST "http://127.0.0.1:8787/mcp/beta" -d "$init"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why./// Renders a loose set of messages in the same `#seq` thread formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.trap 'kill $HUB 2>/dev/null || true' EXITFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.trap 'kill $HUB 2>/dev/null || true' EXITFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.One agent (one MCP client, one bot): paste the token into TELEGRAM_BOT_TOKENFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for telegram-agent-mcp@0.5.0 as of 12 h ago. This is the package itself, not its dependencies.
What would make this Verified
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim clemente-turrubiates: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.