telegram send files
PassAudited by ClawScan on May 1, 2026.
Overview
This skill does what it claims—send selected files to Telegram—but users should understand that files leave the device and Telegram bot credentials are saved locally.
Before installing, confirm you are comfortable with a global CLI that can upload specified files to a configured Telegram chat. Protect the bot token and chat ID, avoid broad file globs on sensitive directories, and use --dry-run when checking what would be sent.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Files selected for sending are uploaded to the configured Telegram chat.
The tool reads the specified local file and sends it to Telegram. This matches the skill purpose, but it means sensitive files can leave the local machine if the user or agent selects the wrong path.
file_data = {"document": (filename or file_path.name, file_path.read_bytes())}
return await self._request("sendDocument", data, files=file_data)Use explicit file paths when possible, review broad patterns like *.pdf before sending, and use --dry-run for sensitive folders.
Anyone with access to the saved config file or environment may be able to use the configured Telegram bot and chat destination.
The tool uses Telegram bot credentials from environment variables or a local config file. This is expected for a Telegram sender, but the registry metadata lists no primary credential or required environment variables.
CONFIG_PATH = Path.home() / ".tsend" / "config.json"
...
return os.getenv("TSEND_TOKEN") or self.get("token")
...
return os.getenv("TSEND_CHAT_ID") or self.get("chat_id")Store bot tokens carefully, restrict access to ~/.tsend/config.json, and rotate the bot token if it may have been exposed.
Installing creates a global tsend command and installs Python dependencies needed by the tool.
The skill is marked as having no install spec, but the documentation instructs users to install a local editable Python package globally. This is purpose-aligned for a CLI tool, but users should notice the install path.
cd <skill-path>/scripts uv tool install -e . ... cd <skill-path>/scripts pip install -e .
Install only from a trusted copy of the skill, and review dependency changes when updating.
