Telegram Send File
Analysis
This skill does what it claims—send user-specified files to Telegram—but users should notice that it uses Telegram bot credentials and may auto-detect the destination chat from local OpenClaw state.
Findings (4)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
with open(file_path, "rb") as fh: ... result = await bot.send_document(document=fh, **upload_kwargs)
The script uploads a user-specified local file to Telegram. This matches the skill purpose, but it is still an external file-sharing action.
pip install python-telegram-bot>=20.0
The skill depends on an external Python package installed manually, while the registry metadata does not declare an install spec or required dependency.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Token File Locations (checked in order) ... TELEGRAM_BOT_TOKEN ... ~/.telegram_bot_token ... ~/.openclaw/openclaw.json → channels.telegram.botToken
The skill uses Telegram bot credentials from environment variables or local configuration files to act as the bot.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
state_path = Path.home() / ".openclaw" / "session-state.json" ... chat_id = inbound.get("chat_id") ... topic_id = int(inbound_topic)The script can route sends based on persistent OpenClaw session-state data rather than an explicit chat ID.
