Skills/PyPI/telegram-ai-cli-mcp

telegram-ai-cli-mcp@0.1.3

CAUTION· not started

Publisher claims: "AI-first CLI and MCP server for Telegram user accounts over MTProto, with plan-and-apply approval, chat allowlists and an audit log for every outgoing message." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher stufently · publishing for 40 daysInstalls 183Last detonated 12 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
TGAI_HTTP_TOKENConfiguration, not credentials: TGAI_CONFIG, XDG_STATE_HOME
Where it talks to
no vendor host named in the codeAlso telegram.org, t.me — 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
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names telegram.org, t.me as well as its own vendor. The guard injects TGAI_HTTP_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx telegram-ai-cli-mcp

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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-19 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; References a credential file in the home directory. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandtests/test_outbox.py:404 · File permission modification command — agent changes file ownership/permissions"""Narrow, *or refuse* — a failed chmod must never fall through to a send.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathstelegram_ai_cli_mcp/roots.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespasses a symlink that sits inside the root and points at ``/etc/shadow``. ItFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathstelegram_ai_cli_mcp/outbox.py:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdelivery mechanism attached — ``~/.ssh/id_ed25519``, the ``.session`` file thatFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
References a credential file in the home directorytelegram_ai_cli_mcp/outbox.py:7 · References a credential file in the home directorydelivery mechanism attached — ``~/.ssh/id_ed25519``, the ``.session`` file thatFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Access to sensitive file pathstests/test_no_private_data.py:172 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesor path.name == ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationtelegram_ai_cli_mcp/config.py:277 · Credential pass-through configuration — agent relays sensitive credentials"""Encryption at rest for api_hash and proxy credentials.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
File permission modification commandtelegram_ai_cli_mcp/archive.py:142 · File permission modification command — agent changes file ownership/permissionsan earlier version, a restore from a backup, or a careless ``chmod -R`` allFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandtelegram_ai_cli_mcp/outbox.py:201 · File permission modification command — agent changes file ownership/permissions``g+w`` is **repaired** (``chmod g-w``), or refused if that fails. It isFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandtelegram_ai_cli_mcp/outbox.py:246 · File permission modification command — agent changes file ownership/permissionsf"chmod g-w {root} — a file this tool sends must be one you put there. "Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Bidirectional text override characters detectedtelegram_ai_cli_mcp/render.py:36 · Bidirectional text override characters detected — may hide content direction_BIDI_CONTROLS = frozenset("‪‫‬‭‮⁦⁧⁨⁩‎‏")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandtelegram_ai_cli_mcp/outbox.py:264 · File permission modification command — agent changes file ownership/permissionsf"chmod g-w {root} — a file this tool sends must be one you put there. "Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Bidirectional text override characters detectedtests/test_render.py:54 · Bidirectional text override characters detected — may hide content direction@pytest.mark.parametrize("bidi", ["‪", "‫", "‬", "‭", "‮", "⁦", "⁩"])Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_config.py:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesThe README, `.env.example` and `docs/configuration.md` all promise the sameFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathstelegram_ai_cli_mcp/outbox.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files``/etc/shadow``. The path is realpathed first, and the result has to be under aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandtelegram_ai_cli_mcp/outbox.py:234 · File permission modification command — agent changes file ownership/permissionssuggestion=f"chmod o-w {root} — a file this tool sends must be one you put there.",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_render.py:60 · Hidden zero-width characters detected — may conceal content@pytest.mark.parametrize("invisible", ["​", "‌", "‍", "⁠", ""])Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commandtelegram_ai_cli_mcp/outbox.py:261 · File permission modification command — agent changes file ownership/permissionsf"{shown} is still writable by other users after chmod "Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Hidden zero-width characters detectedtelegram_ai_cli_mcp/render.py:39 · Hidden zero-width characters detected — may conceal content_INVISIBLE = frozenset("​‌‍⁠")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commandtests/test_archive.py:464 · File permission modification command — agent changes file ownership/permissionscareless `chmod -R` all produce a world-readable copy of somebody's privateFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Dynamic module loadingtests/test_transcribe.py:331 · Dynamic module loadingentrypoint = runpy.run_path("docker/transcribe/entrypoint.py", run_name="contract_only")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandtests/test_secretbox.py:133 · File permission modification command — agent changes file ownership/permissionsassert "chmod 600" in (refusal.value.suggestion or "")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈80 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for telegram-ai-cli-mcp@0.1.3 as of 12 h ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim stufently: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. 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.
  5. Bidirectional text override characters detected≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim stufentlyPropose a patch to the maintainer