telegram
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill communicates with the official Telegram Bot API at
api.telegram.org. This is a well-known service required for the skill's primary functionality. Sensitive credentials likeTELEGRAM_BOT_TOKENare managed via a local.skill.configfile, which prevents the exposure of secrets in the skill's source code.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates sending messages to Telegram, which creates a surface for indirect prompt injection if the agent sends untrusted data through these commands.\n - Ingestion points: The
textfield in TelegramsendMessageAPI calls withinSKILL.md.\n - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are included in the message templates.\n
- Capability inventory: Outbound network communication with the Telegram API via
curl.\n - Sanitization: The skill uses
--data-urlencodeto ensure the integrity of the shell command, but it does not perform content-based filtering or sanitization of the message text.
Audit Metadata