telegram-bot
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network requests to the official Telegram Bot API (api.telegram.org) to facilitate message retrieval and delivery. These operations are essential for the skill's documented purpose.
- [PROMPT_INJECTION]: The skill ingests message content from an external Telegram channel and presents it to the agent, creating a surface for indirect prompt injection where external actors could attempt to override the agent's instructions.
- Ingestion points:
scripts/fetch_dm.pyfetches the latest message from a Telegram channel. - Boundary markers: None. The fetched message text is provided to the agent without delimiters or instructions to treat it as untrusted content.
- Capability inventory: The agent can send messages back to the channel via
scripts/send_channel.pyand has the ability to execute the skill's scripts. - Sanitization: The script only removes the bot's handle from the start of the message; it does not perform sanitization, escaping, or filtering of the core message content.
Audit Metadata