using-telegram-cli
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
@will-17173/telegram-clipackage from the npm registry. This is a vendor-owned resource corresponding to the skill's author. - [COMMAND_EXECUTION]: The skill operates by executing shell commands using the
tgCLI tool (orpnpm devfor local development) to interact with the Telegram API and local message databases. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Telegram messages), creating a surface for indirect prompt injection.
- Ingestion points: Incoming Telegram messages are retrieved via
listen,sync,history, andsearchcommands. - Boundary markers: The skill includes mandatory rules requiring explicit user authorization for all write operations (
send,edit,delete, and group mutations), effectively placing a human-in-the-loop between data ingestion and state-changing actions. - Capability inventory: The skill can execute CLI commands, write to the local file system (database files and JSON/YAML exports), and perform network communications via the Telegram API.
- Sanitization: While the instructions do not specify content-level sanitization for ingested messages, the risk is mitigated by the authorization requirements for any resulting side effects.
Audit Metadata