slim-tg-mcp@0.5.1
CAUTION· static onlyPublisher claims: "Slim Telegram MCP server with skill-based lazy loading, encrypted sessions, and prompt-injection defense" Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso telegram.org — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- nothing has run yet
- What we could not test
- everything: the server has not run yet
Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.
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 analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 52/100 (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; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
"""If `.env.e2e` exists at the repo root, load KEY=VALUE pairs from itFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.audit.log("gif_send", chat=str(req.chat), msg_id=msg_id, doc_id=req.doc_id)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.audit.log("bot_send_keyboard", chat=str(req.chat), msg_id=msg_id, rows=len(rows))Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why..gitignore line for `.env*` so this is safe by default).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.audit.log("sticker_send", chat=str(req.chat), msg_id=msg_id, doc_id=req.doc_id)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."""Authoritative home from /etc/passwd, NOT from $HOME.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_path = PROJECT_ROOT / ".env.e2e"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.auth._session_path("../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.who can influence `$HOME` (poisoned shell init, sudo without -H) couldFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f"If it's our daemon, kill it yourself:\n"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.our originally-inspected pid could kill that daemon (its pid may evenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."could kill the successor daemon"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.audit.log("location_send", chat=str(req.chat), msg_id=msg_id)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.f"If it's hung, stop it manually: kill {info.pid}[/red]"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.shell init, sudo without -H, etc.) could redirect every "persistent" pathFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.'kill None' or 'ps -p None' to the operator."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.daemon = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.f" kill {info.pid} && rm {PID_PATH} {SOCKET_PATH}[/red]"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."""Round-14 MINOR: HOME must come from /etc/passwd, not $HOME.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Bypass _ensure_dirs() chmod calls on tmp_path which already exists.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.`<|im_start|>`, `<system>` tags, etc.) are wrapped inFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.`<|im_start|>`, `<system>` tags, etc.) are wrapped inFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.[[neutralized:'ignore previous instructions']] click here plsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.(`ignore previous instructions`, `you are now`, `[INST]`,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.`[[neutralized:'ignore previous instructions']] click pls`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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 slim-tg-mcp@0.5.1 as of 26 min ago. This is the package itself, not its dependencies.
What would make this Verified
28 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim haoyuwang-haoyuwang88888: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- 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.
- Privileged sudo command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.